Natural language Processing (NLP) has significantly transformed in the last decade, especially in the field of Language Modeling. Large Language Models (LLMs) have achieved SOTA performances on Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in Language Models. In this paper, we examine the different aspects of Language Models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pre-training objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different fine-tuning and In-Context learning techniques used in downstream tasks. It also explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM’s capabilities and raised new challenges. As part of our study, we also inspect LLMs from the lens of scalability to see how their performance is affected by the model’s depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stand.

The rapid advancement of large language models (LLMs), such as ChatGPT, has revolutionized natural language processing, enabling these models to generate coherent and contextually relevant text. These capabilities hold significant potential for various applications, particularly in the medical field. LLMs can assist healthcare professionals by providing accurate information, supporting diagnostic processes, and enhancing medical education. However, the implementation of LLMs in clinical settings faces several barriers, including technical limitations, ethical concerns, regulatory constraints, and practical challenges. Ensuring accuracy, reliability, and interpretability is crucial, along with addressing biases, ensuring data privacy, and establishing ethical guidelines. Future research should focus on improving training techniques, developing explainable AI methods, and creating efficient, resource-saving models. Expanding applications through domain-specific models and multi-modal integration can further unlock the potential of LLMs. By addressing these challenges and prioritizing responsible development, LLM technology can be safely and effectively integrated into various domains, driving innovation and improving outcomes. This paper explores the current state of LLM technology, its medical applications, barriers to implementation, and directions for future research and development

Large Language Models (LLMs) have demonstrated promising capabilities to solve complex tasks in critical sectors such as healthcare. However, LLMs are limited by their training data which is often outdated, the tendency to generate inaccurate ("hallucinated") content and a lack of transparency in the content they generate. To address these limitations, retrieval augmented generation (RAG) grounds the responses of LLMs by exposing them to external knowledge sources. However, in the healthcare domain there is currently a lack of systematic understanding of which datasets, RAG methodologies and evaluation frameworks are available. This review aims to bridge this gap by assessing RAG-based approaches employed by LLMs in healthcare, focusing on the different steps of retrieval, augmentation and generation. Additionally, we identify the limitations, strengths and gaps in the existing literature. Our synthesis shows that proprietary models such as GPT-3.5/4 are the most used for RAG applications in healthcare. Also, there is a lack of standardized evaluation frameworks for RAG-based applications. In addition, the majority of the studies do not assess or address ethical considerations related to RAG in healthcare. It is important to account for ethical challenges that are inherent when AI systems are implemented in the clinical setting. Lastly, we highlight the need for further research and development to ensure responsible and effective adoption of RAG in the medical domain.

LLMs are a compressed repository of a vast corpus of valuable information on which they are trained. Therefore, this work hypothesizes that LLMs such as Llama, Orca, Falcon, and Mistral can be used for misinformation detection by making them cross-check new information with the repository on which they are trained. Accordingly, this paper describes the findings from the investigation of the abilities of LLMs in detecting misinformation on multiple datasets. The results are interpreted using explainable AI techniques such as LIME, SHAP, and Integrated Gradients. The LLMs themselves are also asked to explain their classification. These complementary approaches aid in better understanding the inner workings of misinformation detection using LLMs and lead to conclusions about their effectiveness at the task.

With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) Relative Importance and Activations (RIA), a new pruning metric that jointly considers the weight and activations efficiently on LLMs; and 2) Channel Permutation, a new approach to maximally preserve important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies’ environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% (1252 W for A100 with AMD EPYC 7V13 vs 613 W for Intel® Xeon® Gold 6538N) while providing production ready throughput & latency.

This paper explores the application of Large Language Models (LLMs), such as GPT-3 and GPT-4, in generating cybersecurity policies and strategies to mitigate ransomware threats, including data theft ransomware. We discuss the strengths and limitations of LLMs for ransomware defense and provide recommendations for effectively leveraging LLMs while ensuring ethical compliance. The key contributions include a quantitative evaluation of LLM-generated policies, an examination of the legal and ethical implications, and an analysis of how LLMs can enhance ransomware resilience when applied judiciously.

This paper proposes the utilization of large language models as recommendations systems for museums. Since the aforementioned models lack the notion of context, they can’t work with temporal information that is often present in recommendations for cultural environments (e.g. special exhibitions or events). In this respect, the current work aims at enhancing the capabilities of large language models through a fine-tuning process that incorporates contextual information and user instructions. The resulting models are expected to be capable of providing personalized recommendations, aligned with user preferences and desires. More specifically, Generative Pre-trained Transformer 4, a knowledge-based large language model is fine-tuned and turned into a context-ware recommendation system, adapting its suggestions based on user input and specific contextual factors such as location, time of visit, and other relevant parameters. The effectiveness of the proposed approach is evaluated through certain user studies, which ensure an improved user experience and engagement within the museum environment.

Although learning analytics (LA) holds great potential to improve teaching and learning, LA research and practice are currently riddled with limitations that impact every stage of the LA life cycle. The present paper offers an overview of these challenges before proposing strategies to overcome them and exploring how the recent innovations brought forth by language models can improve LA research and practice. In particular, we encourage the empowerment of teachers during LA development, as this would strengthen the theoretical foundation of LA solutions and increase their interpretability and usability. Furthermore, we provide examples of how process data can be used to understand learning processes and generate more interpretable LA insights. Furthermore, we explore how LLMs could come into play in LA to generate interpretable insights, timely and actionable feedback, increase personalization, and support teachers’ tasks more broadly.

Structured science summaries or research contributions using properties or dimensions beyond traditional keywords enhances science findability. Current methods, such as those used by the Open Research Knowledge Graph (ORKG), involve manually curating properties to describe research papers' contributions in a structured manner, but this is labor-intensive and inconsistent between the domain expert human curators. We propose using Large Language Models (LLMs) to automatically suggest these properties. However, it's essential to assess the readiness of LLMs like GPT-3.5, Llama 2, and Mistral for this task before application. Our study performs a comprehensive comparative analysis between ORKG's manually curated properties and those generated by the aforementioned state-of-the-art LLMs. We evaluate LLM performance through four unique perspectives: semantic alignment and deviation with ORKG properties, fine-grained properties mapping accuracy, SciNCL embeddings-based cosine similarity, and expert surveys comparing manual annotations with LLM outputs. These evaluations occur within a multidisciplinary science setting. Overall, LLMs show potential as recommendation systems for structuring science, but further finetuning is recommended to improve their alignment with scientific tasks and mimicry of human expertise.

This survey provides a comprehensive overview of in-context learning (ICL) in large language models (LLMs), a phenomenon where models can adapt to new tasks without parameter updates by leveraging task-relevant information within the input context. We explore the definition and mechanisms of ICL, investigate the factors contributing to its emergence, and discuss strategies for optimizing and effectively utilizing ICL in various applications. Through a systematic review of recent literature, we first clarify what ICL is, distinguishing it from traditional fine-tuning approaches and highlighting its unique characteristics. We then delve into the underlying causes of ICL, examining theories ranging from implicit meta-learning during pre-training to the emergence of task vectors in LLMs. The survey also covers various approaches to enhance ICL performance, including prompt engineering techniques, demonstration selection strategies, and methods for improving generalization across diverse tasks. Additionally, we discuss the limitations and challenges of ICL, such as its sensitivity to demonstration ordering and potential biases. By synthesizing findings from numerous studies, we aim to provide researchers and practitioners with a clear understanding of the current state of ICL research, its practical implications, and promising directions for future investigation. This survey serves as a valuable resource for those seeking to leverage ICL capabilities in LLMs and contributes to the ongoing discourse on the remarkable adaptability of these models.

As modern technologies, particularly home assistant devices, become more integrated into our daily lives, they are also making their way into the domain of energy management within our homes. Homeowners, now acting as prosumers, have access to detailed information in 15-minute or even 5-minute intervals, including weather forecasts, outputs from Renewable Energy Sources (RES)-based systems, appliance schedules and the current energy balance, which details any deficits or surpluses along with their quantities and the predicted prices on the Local Energy Market (LEM). The goal for these prosumers is to reduce costs while ensuring their home’s comfort levels are maintained. However, given the complexity and the rapid decision-making required in managing this information, the need for a supportive system is evident. This is particularly true given the routine nature of these decisions, highlighting the potential for a system that provides personalized recommendations to optimize energy consumption, whether that involves adjusting the load or engaging in transactions with the LEM. In this context, we propose a recommendation system powered by Large Language Models (LLM), Scikit-llm and Zero-Shot Classifiers, designed to evaluate specific scenarios and offer tailored advice for prosumers based on the available data at any given moment. Two scenarios for a prosumer of 5.9 kW are assessed using candidate labels, such as Decrease, Increase, Sell and Buy.

Cognitive Warfare (CogWar) is another form of warfare where the goal is to exploit cognition facets to disrupt, undermine, influence or modify human decisions. Famous examples include “Operation Gidlock” meddling with the US 2016 election, and CogWar campaigns assisting the annexation of Crimea. As Large Language Model(LLM)-based applications expand, reaching more users and their cognitive states, stealth Malicious Cognitive Behavioral Tactics (MCBT) can be embedded in trusted application sessions to systematically profile, then alter, each individual’s cognition over time. Successful MCBT can create more cases like Snowden, mass shootings, or January6. This short-form paper discusses a novel MCBT threat model, a novel kill chain, and an on-going prototype for demonstration.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

Obsessive-Compulsive Disorder (OCD) is a mental health condition marked by recurrent intrusive thoughts or sensations that compel individuals to perform repetitive behaviors or mental acts. Obsessions and compulsions significantly disrupt daily life and cause considerable distress. Early identification and intervention improve long-term outcomes. This study aimed to evaluate the ability of four advanced artificial intelligence models (ChatGPT-3.5, ChatGPT-4, Claude, and Bard) to accurately recognize OCD compared to human professionals and to assess recommended therapies and stigma attributions. This study was conducted during March 2024 utilizing 12 vi-gnettes. Each vignette depicted a client, either a young adult or a middle-aged male or female, attending an initial therapy session. Each vignette was evaluated ten times, resulting in 480 evaluations. The results were compared with those of a human sample of 514 psychotherapists, as reported by Canavan. Significant differences were found. AI models demonstrated higher OCD recognition rates and confidence levels than human professionals and showed 100% confidence in recognition, compared to 87% among psychotherapists. AI models also recommended evi-dence-based interventions more frequently, with ChatGPT-3.5 and Claude at 100%, ChatGPT-4 at 90%, and Bard at 60%, compared to 61.9% among psychotherapists. Additionally, AI models ex-hibited significantly lower stigma and danger estimations, though both AI and psychotherapists demonstrated high willingness to treat the described cases. The findings suggest that AI models surpass human professionals in recognizing OCD and recommending evidence-based treatments while also demonstrating lower stigma. These results highlight the potential of AI tools to enhance OCD diagnosis and treatment in clinical settings.

Backgrounds: The field of Artificial Intelligence (AI) has seen a major shift in recent years due to the development of new Machine Learning (ML) models such as Generative Pre-trained Transformer (GPT) and AI which are progressively becoming part our everyday lives. GPT has achieved previously unheard-of levels of accuracy in most computerized language processing tasks and their chat-based variations. Aim: The aim of this study was to investigate the problem-solving abilities of ChatGPT using two sets of verbal insight problems, with a known performance level established by a sample of human participants. Material and Methods: A total of 30 problems labelled as “practice problems” and “transfer problems”, as listed by Ansburg and Dominowski (2000), were administered to ChatGPT. The answers provided by ChatGPT received a score of "0" for each problem answered incorrectly and a score of "1" for each correct response, as per the correct solution specified in Ansburg and Dominowski's (2000) study. The highest score that could be attributed to both the practice and transfer problems was 15 out of 15. In order to compare ChatGPT performance to the performance to that of human subjects, the solution rate for each problem (based on a sample of 20 subjects) was used, as indicated by Ansburg and Dominowski (2000). Results: The study highlighted that ChatGPT can be trained in out-of-the-box thinking and demonstrated potential in solving verbal insight problems. The global performance of ChatGPT equalled the most probable outcome for the human sample in both practice problems and transfer problems as well as upon their combination. Additionally, ChatGPT answer combinations were among the 5% of most probable outcomes for the human sample both when considering practice problems and pooled problem sets. These findings demonstrate that ChatGPT performance on both set of problems was in line with the mean rate of success of human subjects, indicating that it performed reasonably well. Conclusions: The use of transformer architecture and self-attention in ChatGPT may have helped to prioritize inputs while predicting, contributing to its potential in verbal insight problem-solving. ChatGPT has shown potential in solving insight problems, thus highlighting the importance of incorporating AI in psychological research. However, it is acknowledged that open challenges still exist. Indeed, further research is needed to fully understand the capabilities and limitations of AI in insight problem-solving.

Musyakalah is one of the Arabic linguistic styles included under the category of majaz. This style is commonly used in Al-Quran. The Indonesian translation of Al-Quran is a case where many of the figures of speech are translated literally, thereby causing serious semantic problems. Thus, the research problem of this is formulated with the following questions: 1) How many musyakalah ayahs are there in Al-Quran?; 2) How are the musyakalah ayahs translated, literally (harfiyya) or interpretatively (tafsiriyya)?; 3) How many ayahs are translated literally and how many are translated interpretatively?; and 4) Which translated musyakalah ayahs have the potential to raise semantic and theological problems? The corpus in this research consists of all musyakalah ayahs in Al-Quran and their translation to Indonesian published by the Department of Religious Affairs of Indonesia. The research adopted a descriptive-semantic method. The findings of this research are: 1) There are only eleven ayahs in Al-Quran using musyakalah style, namely: Alhasyr ayah 19, Ali Imran ayah 54, Annaml ayah 50, Alanfal ayah 30, Asysyura ayah 40, Albaqarah ayah 15, Almaidah 116, Aljatsiah ayah 34, Attaubah ayah 79, Annisa ayah 142, and Albaqarah 194; 2) The musyakalah ayahs translated literally are: Aljatsiah 34, Almaidah 116, Asysura 40, Annaml 50, and Alhasyr 19, whereas the musyakalah ayahs translated interpretatively are Albaqarah 194, Annisa 142, Attaubah 79, Albaqarah 15, Alanfal 30, and Ali Imran 54; 3) Of the eleven musyakalah ayahs, only Alhasyr ayah 19 that is translated correctly and does not have the potential of creating misinterpretation. Meanwhile, the interpretation of the other four ayahs can potentially cause misinterpretation or are against the basic principles of Islam. The six remaining ayahs are translated interpretatively and thus do not have the potential to be misinterpreted; 4) The findings suggest that musyakalah ayahs are more appropriately translated interpretatively. Therefore, the following is recommended: 1) Considering the different characteristics of Arabic and Indonesian languages, studies on Al-Quran translation into Indonesian should continuously be carried out; 2) In order to avoid misinterpretation, it is better that the translation of musyakalah ayahs uses tafsiriyya (interpretative) approach; 3) The harfiyya (literal) and tafsiriyya (interpretative) approaches should be developed for other styles beside musyakalah..

Background: People with Down syndrome (DS) have a trisomy of chromosome 21 and marked deficits in verbal memory but relatively preserved visuospatial perception. Verbal memories are related to semantic knowledge. Little is known about the organization of semantic knowledge in people with DS, which was the aim of this study. Aims: The extent of false memory in people with DS was examined. Possible differences in the number of false memories induced by nominal and verbal themes were examined. Methods and Procedures: In the study phase, ten word lists with semantically related associates were presented. In the recognition phase, participants made judgments on whether each word had been represented previously as semantically related lures, old words, and semantically unrelated new words. Outcomes and Results: Differences in the processing of nominal and verbal theme-related lures were observed among people with DS. When processing nominal theme-related lures, people with DS showed delayed false positives. When processing verbal theme-related lures, people with DS showed no differences compared to controls. Similar patterns have been observed in people with DS when processing nominal theme-related associates and verbal theme-related associates. People with DS have delayed recognition of associates. When processing unrelated words, they showed significantly higher false positives than controls for both nominal and verbal eliciting themes. Further analyses of the themes revealed differences in false positives across syntactic categories among groups. Conclusions and Implications: People with DS showed a delayed recognition of associates and deviance in recognizing unrelated words in the nominal and verbal theme categories. People with DS were delayed in terms of nouns, but deviated with verbs in associated and unrelated words. Additionally, people with DS showed distinct patterns in processing five nominal lures and three verbal lures, suggesting that they formed false memories differently based on distinct syntactic categories. Thus, it was concluded that people with DS develop a deviant semantic structure. Category-based interventions for people with DS should be implemented in order to improve their semantic knowledge through lexical connections.

Tactics, Techniques, and Procedures (TTPs) constitute the most valuable aspect of Cyber Threat Intelligence (CTI). However, TTPs are often implicit in unstructured text, necessitating manual analysis by field experts. Automating the classification of TTPs from unstructured text is a crucial task in contemporary research. MITRE ATT&CK serves as the de facto standard for studying TTPs. Existing research constructs classification datasets based on its procedural examples for tactics and techniques. However, due to a significant proportion of small sample categories, a long-tail phenomenon exists, leading to a highly imbalanced sample distribution. Consequently, more research concentrates on categories with relatively abundant samples. This paper proposes a method that combines ChatGPT data augmentation with Instruction Supervised Fine-Tuning of open large language models. This approach offers a solution for TTPs classification in few-shot learning scenarios, achieving coverage of 625 technical categories. The Precision, Recall, and F1 scores reach 86.2%, 89.9%, and 87.3%, respectively.

This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.

(1) Background: Artificial Intelligence (AI) models have shown potential in various educational contexts. However, their utility in explaining complex biological phenomena, such as Intrinsically Disordered Proteins (IDPs), requires further exploration. This study empirically evaluated the performance of various Large Language Models (LLMs) in the educational domain of IDPs. (2) Methods: Four LLMs, GPT-3.5, GPT-4, GPT-4 with Browsing, and Google Bard (PaLM 2), were assessed using a set of IDP-related questions. An expert evaluated their responses across five categories: accuracy, relevance, depth of understanding, clarity, and overall quality. Descriptive statistics, ANOVA, and Tukey's honesty significant difference tests were utilized for analysis. (3) Results: The GPT-4 model consistently outperformed the others across all evaluation categories. Although GPT-4 and GPT-3.5 were not statistically significantly different in performance (p>0.05), GPT-4 was preferred as the best response in 13 out of 15 instances. The AI models with browsing capabilities, GPT-4 with Browsing and Google Bard (PaLM 2) displayed lower performance metrics across the board with statistically significant differences (p<0.0001). (4) Conclusion: Our findings underscore the potential of AI models, particularly LLMs such as GPT-4, in enhancing scientific education, especially in complex domains such as IDPs. Continued innovation and collaboration among AI developers, educators, and researchers are essential to fully harness the potential of AI for enriching scientific education.

The increased complexity of modern systems is calling for an integrated and comprehensive approach to system design and development and in particular, a shift towards Model-Based Systems Engineering (MBSE) approaches for system design. The requirements that serve as the foundation for these intricate systems are still primarily expressed in Natural Language (NL), which can contain ambiguities and inconsistencies that hinder their direct translation into models. The colossal developments in the field of Natural Language Processing (NLP) in general and Large Language Models (LLMs) in particular can serve as an enabler for the conversion of NL requirements into semi-machine-readable requirements. This is expected to facilitate their standardization and use in a model-based environment. This paper discusses a two-fold strategy for converting NL requirements into semi-machine-readable requirements using language models. The first approach involves creating a requirements table by extracting information from free-form NL requirements. The second approach is an agile methodology that facilitates the identification of boilerplate templates for different types of requirements based on observed linguistic patterns. For this study, three different LLMs were utilized. Two of these models were fine-tuned versions of Bidirectional Encoder Representations from Transformers (BERT), specifically aeroBERT-NER and aeroBERT-Classifier, which were trained on annotated aerospace corpora. Another LLM, called flair/chunk-english, was utilized to identify sentence chunks present in NL requirements. All three language models were utilized together to achieve the standardization of requirements. To demonstrate the effectiveness of the methodologies, requirements from Parts 23 and 25 of Title 14 Code of Federal Regulations (CFRs) were employed, and a total of two, five, and three boilerplate templates were identified for design, functional, and performance requirements, respectively.

To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.

Bio-molecular reagents like antibodies required in experimental biology are expensive and their effectiveness, among other things, is critical to the success of the experiment. Although such resources are sometimes donated by one investigator to another through personal communication between the two, there is no previous study to our knowledge on the extent of such donations, nor a central platform that directs resource seekers to donors. In this paper, we describe, to our knowledge, a first attempt at building a web-portal titled Bio-Resource Exchange that attempts to bridge this gap between resource seekers and donors in the domain of experimental biology. Users on this portal can request for or donate antibodies, cell-lines and DNA Constructs. This resource could also serve as a crowd-sourced database of resources for experimental biology. Further, in order to index donations outside of our portal, we mined scientific articles to find instances of donations of antibodies and attempted to extract information about these donations at the finest granularity. Specifically, we extracted the name of the donor, his/her affiliation and the name of the antibody for every donation by parsing the acknowledgements sections of articles. To extract annotations at this level, we propose two approaches – a rule based algorithm and a bootstrapped relation learning algorithm. The algorithms extracted donor names, affiliations and antibody names with average accuracies of 57% and 62% respectively. We also created a dataset of 50 expert-annotated acknowledgements sections that will serve as a gold standard dataset to evaluate extraction algorithms in the future. Contact: [email protected], [email protected] Database URL: http://tonks.dbmi.pitt.edu/brx Supplementary information: Supplementary data are available at Database online.

The accurate diagnosis and effective treatment of mental health disorders such as depression remain challenging owing to the complex underlying causes and varied symptomatology. Traditional information extraction methods struggle to adapt to evolving diagnostic criteria such as the Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5) and to contextualize rich patient data effectively. This study proposes a novel approach for enhancing information extraction from mental health data by integrating medical knowledge graphs and large language models (LLMs). Our method leverages the structured organization of knowledge graphs specifically designed for the rich domain of mental health combined with the powerful predictive capabilities and zero-shot learning abilities of LLMs. This research enhances the quality of knowledge graphs through entity linking and demonstrates superiority over traditional information extraction techniques, making a significant contribution to the field of mental health. It enables a more fine-grained analysis of the data and the development of new applications. Our approach redefines the manner in which mental health data are extracted and utilized. By integrating these insights with existing healthcare applications, the groundwork is laid for the development of real-time patient monitoring systems. The performance evaluation of this knowledge graph highlights its effectiveness and reliability, indicating significant advancements in automating medical data processing and depression management.

Virtual assistants (VAs) have gained widespread popularity across a wide range of applications, and the integration of Large Language Models (LLMs) such as ChatGPT has opened up new possibilities for developing even more sophisticated VAs. However, this integration poses new ethical issues and challenges that must be carefully considered, particularly as these systems are increasingly used in public services: transfer of personal data, decision-making transparency, potential biases, and privacy risks. This paper, an extension of the work presented at IberSPEECH 2022, analyzes the current regulatory framework for AI-based VAs in Europe and delves into ethical issues in depth, examining potential benefits and drawbacks of integrating LLMs with VAs. Based on the analysis, this paper argues that the development and use of VAs powered by LLMs should be guided by a set of ethical principles that prioritize transparency, fairness, and harm prevention. The paper presents specific guidelines for the ethical use and development of this technology, including recommendations for data privacy, bias mitigation, and user control. By implementing these guidelines, the potential benefits of VAs powered by LLMs can be fully realized while minimizing the risks of harm and ensuring that ethical considerations are at the forefront of the development process.

Despite the growing capabilities of large language models, concerns exist about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers that can be useful in a variety of industries, especially ones that are “restricted” and have limited data. We consider that bias can occur due to intrinsic model architecture and dataset quality. The two aspects are evaluated using two different metrics we created. We show that our dataset augmentation algorithm reduces bias as measured by our metrics.

This paper examines the potential of large language models, specifically ChatGPT, BingChat, and Bard, in enhancing the work of teachers in various educational settings. These models, powered by cutting-edge artificial intelligence, offer a wide range of applications that can aid educators in curriculum development, personalized instruction, student engagement, and administrative tasks. By harnessing the capabilities of these language models, teachers can not only streamline their workload but also improve the overall quality of education. This paper explores the ways in which these models can empower educators and revolutionize teaching practices.

The study aimed to determine the effect of heat stress (HS) on reproductive parameters [calving to first service (CTFS) and first service conception rate (FSCR)] and general physiological responses [rectal temperature (RT) and respiratory rate (RR)] in tropical Holstein Friesian dairy cows raised in Ratchaburi province, Thailand. Cows were divided into a moderate HS (n = 22) and a mild HS (n = 22) group. Cycling cows were detected and injected with PGF2α at the beginning of the experimental period. Reproductive and physiological parameters were recorded. The average temperature humidity indices experienced by the cows were 80.67 ± 0.79 and 77.81 ± 1.09 for the moderate and mild HS groups, respectively. Cows showed significantly lower RT and RR in the mild (38.47 ± 0.21°C and 41.04 ± 4.55 bpm, respectively) than in the moderate HS group (38.87 ± 0.15°C and 51.17 ± 10.52 bpm). Under mild HS, cows showed a better response to injection of PGF2α than those under moderate HS. The percentage of cows that ovulated after being induced by PGF2α and showed estrus signs was higher in the mild than the moderate HS groups (54.55% versus 18.18%). Furthermore, the FSCR of cows under mild HS tended to be higher than in the moderate HS group (54.55 % and 42.11%, respectively), while the average CTFS interval was significantly shorter under mild than moderate HS (69.47 ± 18.18 and 84.60 ± 27.68, respectively). These results indicate that HS impairs reproductive performance in cross-bred Holstein cows, especially in moderate HS conditions.

RNA sequencing techniques, like bulk RNA-seq and Single Cell (sc) RNA-seq, are critical tools for the biologist looking to analyze the genetic activity/transcriptome of a tissue or cell during an experimental procedure. Platforms like Illumina's next-generation sequencing (NGS) are used to produce the raw data for this experimental procedure. This raw FASTQ data must then be prepared via a complex series of data manipulations by bioinformaticians. This process currently takes place on an unwieldy textual user interface like a terminal/command line that requires the user to install and import multiple program packages, preventing the untrained biologist from initiating data analysis. Open-source platforms like Galaxy have produced a more user-friendly pipeline, yet the visual interface remains cluttered and highly technical, remaining uninviting for the natural scientist. To address this, SeqMate is a user-friendly tool that allows for one-click analytics by utilizing the power of a large language model (LLM) to automate both data preparation and analysis (differential expression, trajectory analysis, etc). Furthermore, by utilizing the power of generative AI, SeqMate is also capable of analyzing such findings and producing written reports of upregulated/downregulated/user-prompted genes with sources cited from known repositories like PubMed, PDB, and Uniprot.

Transmission of values and religious concepts to children is one of the most important issues in the third millennium and it has drawn varied and different views among experts and scholars in the world. Research specialized in religious literature for children and adolescents create new capacities in the presentation of religious concepts to the group. Plans have been considered to transfer values and religious concepts in the curricula of primary school children in the group in Iran. It is one of the topics that the authors note to the introduction of the minutiae of religion in the first three elementary grades. In this study, the collection and analysis methods providing content related to the minutiae of religion in reading books the first till third sections of the years 2013-2015. In addition, the plan includes aspects of other branches of religion in these books on information collected from text books that collected and classified. The result is that "definitely good and forbidding the evil" and "prayer" have the highest frequency of applications in the selected books. Further branches made of branches of religion in these books, represents the values of religious, moral and social as well.

: Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The re-sults demonstrated that both multi-agent models—Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents—significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 ex-celled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative re-finements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field.

Estimating Visual Quality of Street Space (VQoSS) is pivotal for urban design, environmental sustainability, civic engagement, etc. Recent advancements, notably in deep learning, have enabled large-scale analysis. However, traditional deep learning approaches are hampered by extensive data annotation requirements and limited adaptability across diverse VQoSS tasks. Multimodal Large Language Models (MLLMs) have recently demonstrated proficiency in various computer vision tasks, positioning them as promising tools for automated VQoSS assessment. In this paper, we pioneer the application of MLLMs to VQoSS change estimation, with our empirical findings affirming their effectiveness. In addition, we introduce Street Quality GPT (SQ-GPT), a model that distills knowledge from the current most powerful but inaccessible (not free) GPT-4, requiring no human efforts. SQ-GPT approaches GPT-4’s performance and is viable for large-scale VQoSS change estimation. In a case study of Nanjin, we showcase the practicality of SQ-GPT and knowledge distillation pipeline. Our work promises to be a valuable asset for future urban studies research.

This study aimed to investigate the appearance and frequencies of the booroola polymorphism of the bone morphogenetic protein receptor 1b (BMPR1B) gene (FecB) and the embrapa polymorphism of the growth differentiation factor 9 (GDF9) gene (FecGE) in sheep in Thailand. A total of 454 cross-bred sheep blood samples were collected from four provinces in Thailand during August 2022 to July 2023. The polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) method was used to identify the FecB and FecGE genotype. The history of ewe birth types was collected from the owners to analyze the association between Fecundity (Fec) genotypes and the history of birth types. The genotypic frequencies of FecB for homozygous genotype (B/B), heterozygous genotype (+/B) and wild-type (+/+) were 0.22%, 1.54%, and 98.24%, respectively. Meanwhile, the genotypic frequencies of FecGE for homozygous genotype (E/E), heterozygous genotype (+/E), and wildtype (+/+) were 0.00%, 2.42%, and 97.58%, respectively. Furthermore, three ewes exhibited both FecB and FecGE genotypes. Fisher’s exact test revealed that the possessor of FecB genotype was associated with multiple births (p<0.01). Both FecB and FecGE mutations were identified in crossbred sheep in Thailand. Sheep containing FecB allele is a better candidate to be selected to improve the prolificacy of crossbred sheep in Thailand.

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can integrate seamlessly into societal frameworks requiring nuanced understanding and decision-making. Zero-Shot Instance Retrieval (ZSIR) stands at the forefront of this endeavour, potentially providing a robust platform for AI systems, particularly large visual language models, to demonstrate and refine cognition-aligned learning without the need for direct experience. In this paper, we critically evaluate current cognition alignment methodologies within traditional zero-shot learning paradigms, using visual attributes and word embedding generated by large AI models. We propose a unified similarity function that quantifies the cognitive alignment level, bridging the gap between AI processes and human-like understanding. Through extensive experimentation, our findings illustrate that this similarity function can effectively mirror the visual-semantic gap, steering the model towards enhanced performance in zero-shot instance retrieval. This work not only benchmarks the cognition alignment of AI, but also sets a new precedent for the development of visual language models attuned to the complexities of human cognition.}

Large language models (LLMs) have shown impressive performance and versatility. However, their billions of parameters and high computational costs hinder the development of personalized and privacy-preserving AI assistants operating locally on user devices. In this work, we explored the potential of pruning LLMs to create lightweight models suitable for user devices, using the moderate-sized Llama-2 7B model as an example. By adopting a simple yet effective pruning method, we found that up to 60% of the weights in the Llama-2 7B model could be pruned without significantly impairing its language modeling capabilities. Furthermore, despite occasional factual inaccuracies, the pruned model at the sparsity limit generated fluent and helpful answers to daily queries, demonstrating its feasibility of on-device AI assistants. These inaccuracies might originate from forgetting or hallucination due to pruning. We proposed a simple protocol to distinguish between the two mechanisms, as well as future directions to improve the pruned models for local AI assistants.

Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks such as machine translation, question answering, text summarization, and natural language understanding. Recent research has shown that utilizing ChatGPT for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level but performs poorly at the segment level. To further improve the performance of LLMs on MT quality assessment, we conducted an investigation into several prompting methods. Our results indicate that by combining Chain-of-Thoughts and Error Analysis, a new prompting method called Error Analysis Prompting, LLMs like ChatGPT can \textit{generate human-like MT evaluations at both the system and segment level}. Additionally, we discovered some limitations of ChatGPT as an MT evaluator, such as unstable scoring and biases when provided with multiple translations in a single query. Our findings aim to provide a preliminary experience for appropriately evaluating translation quality on ChatGPT while offering a variety of tricks in designing prompts for in-context learning. We anticipate that this report will shed new light on advancing the field of translation evaluation with LLMs by enhancing both the accuracy and reliability of metrics. The project can be found at https://github.com/Coldmist-Lu/ErrorAnalysis_Prompt.

Sustainable development and education in sustainable development (ESD) are crucial and interconnected topics under wide discussion today. Young adults need to be educated in how to help bring about change. Thus, the dynamic relationship between school and home is important. In education, use could be made of English language classes, especially since English is a global language that enables access to the sustainability literature and facilitates discussion in global conferences and meetings. Consequently, English as a foreign language (EFL) students could gain confidence from being able to understand and use the terminology of, for example, sustainability. In this paper, the use of competence-based language teaching (CBLT) is proposed as a means of introducing sustainability topics into EFL writing classes at a university in Saudi Arabia. Students’ competence in sustainable development is therefore considered based on their ability to write about suggested sustainable development topics, measured on a scale for five dimensions of ESD proposed by Michelsen and Fischer (2017). The results demonstrate that the students possessed competence in sustainable development and intended to participate in its implementation. Thus, recommendations are made for the stakeholders in the education sector to include sustainable development topics as an initial offering in the curricula of various specialties using the CBLT approach.

ChatGPT, a Large Language Model (LLM) utilizing Natural Language Processing (NLP), has caused concerns about its impact on job sectors, including cybersecurity. In this study, we assessed ChatGPT’s impacts in non-managerial cybersecurity roles using the NICE Framework and Technological Displacement theory. We also explored its potential in passing top cybersecurity certification exams. Findings revealed ChatGPT’s promise in streamlining some jobs, especially those requiring memorization. Moreover, we highlighted ChatGPT’s challenges and limitations, such as ethical implications, LLM limitations, and Artificial Intelligence (AI) security. The study suggests that LLMs like ChatGPT could transform the cybersecurity landscape, causing job losses, skill obsolescence, labor market shifts, and mixed socioeconomic impacts. We recommend a shift in focus from memorization to critical thinking, and collaboration between LLM developers and cybersecurity professionals.

The proliferation of deep learning in natural language processing (NLP) has led to the development and release of innovative technologies capable of understanding and generating human language with remarkable proficiency. Atinuke, a Transformer-based neural network, optimises performance across various language tasks by utilising a unique configuration. The architecture interweaves layers for processing sequential data with attention mechanisms to draw meaningful affinities between inputs and outputs. Due to the configuration of its topology and hyperparameter tuning, it can emulate human-like language by extracting features and learning complex mappings. Atinuke is modular, extensible, and integrates seamlessly with existing machine learning pipelines. Advanced matrix operations like softmax, embeddings, and multi-head attention enable nuanced handling of textual, acoustic, and visual signals. By unifying modern deep learning techniques with software design principles and mathematical theory, the system achieves state-of-the-art results on natural language tasks whilst remaining interpretable and robust.

Since the beginning of the internet era, there has been an explosion of growth in structured data (such as numbers, symbols, and labels) as well as unstructured data (including images, videos, and text). Efficient and accurate mixed query of these two types of data is a key technology to achieve high-quality information retrieval, and it is also a major challenge that needs to be solved urgently in the industry. In this study, we employ an advanced Transformer model that combines strategies and fine-tuning techniques for multi-task learning. Specifically, the model is first pre-trained on a large-scale, general-purpose dataset to learn different types of data representations and basic language comprehension skills. After that, we fine-tuned the parameters of the model to better suit these specific data processing tasks for specific application scenarios, such as image annotation, video content analysis, and structured data query. At the heart of the model is the self-attention mechanism, which allows the model to automatically emphasize the important parts and ignore irrelevant information when processing the input data. In addition, we have introduced task-specific adaptation layers that are designed to add additional processing power to the original Transformer architecture, such as a semantic analysis layer for unstructured text data and a relational extraction layer for structured data. This combination of general pre-training and task-specific fine-tuning allows the model to flexibly process and integrate information from different data sources, improving processing efficiency and accuracy. Experimental results show that the model performs well in a variety of data processing tasks, significantly improves the accuracy and efficiency of information retrieval, and verifies the strong potential and adaptability of large language models in processing mixed data types.

This Special Issue of Humanities comes at a time when the viability of the humanities are challenged on numerous fronts. On the one hand, the humanities face material threats as the politics of austerity continues throughout Europe and the United States, diminishing public support and making profit margin and “job creation” the primary measure of value or the basis of state university funding decisions. On the other, the humanities face conceptual, theoretical and ethical challenges, as the emergence of post-racial and post-humanist discourses signal what Foucault called “a change in the fundamental arrangements of knowledge.” The defining boundaries of constructs such as “race” and “human” have been radically called into question, challenging us to rethink the classificatory systems that found hierarchical relationships between, for example, the “fully human” and sub-human or non-human others. Despite dominant nations’ professed commitment to a universal human rights paradigm, racialized identities are still often the targets of disenfranchisement and dehumanization, while the exploitation and destruction of the natural world continues in the name of “progress” and profits.

Considering that emotional events diversify as one ages, this study formulates the Salient Episodic Memory Aggregation Hypothesis, which claims that aging induces homogenization of episodic memory and consequently increases the salience of emotional episodes. To test this hypothesis, the study focused on sadness episodic memory and conducted a web-based survey and a combined analysis consisting of natural language processing, machine learning, and network graph analysis. A sample of 2,954 adults aged between their 20s and over 70s participated in this study. They were asked to describe a sad event they had experienced and assess the psychological properties of the recalled episodes. After isolating and lemmatizing episodic words using natural language processing, vocabulary frequency was counted for each generation, and network graph analysis based on machine learning was performed to compare the structures of sadness episodes between generations. As a result, there were mainly two types of episodic words for which frequencies either declined or increased with age. The network structures of episodic words for the older generations possessed higher proximity (shortest path length) to higher concentrations of episodic words. These findings support the current hypothesis, indicating that the nature of sadness episodes differ between generations, and that older people have more aggregated episodic memory structures.

The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for Arabic. These models, including ArabianGPT-0.1B and ArabianGPT-0.3B, vary in size and complexity, aligning with the nuanced linguistic characteristics of Arabic. The AraNizer tokenizer, integral to these models, addresses the unique morphological aspects of Arabic script, ensuring more accurate text processing. Empirical results from fine-tuning the models on tasks like sentiment analysis and summarization demonstrate significant improvements. For sentiment analysis, the fine-tuned ArabianGPT-0.1B model achieved a remarkable accuracy of 95%, a substantial increase from the base model's 56%. Similarly, in summarization tasks, fine-tuned models showed enhanced F1 scores, indicating improved precision and recall in generating concise summaries. Comparative analysis of fine-tuned ArabianGPT models against their base versions across various benchmarks reveals nuanced differences in performance, with fine-tuning positively impacting specific tasks like question answering and summarization. These findings underscore the efficacy of fine-tuning in aligning ArabianGPT models more closely with specific NLP tasks, highlighting the potential of tailored transformer architectures in advancing Arabic NLP.

Current neural network models can demonstrate reasonable-looking behavior, considered by some developers and researchers human-like. For example, a large language model GPT-3 is susceptible to human-like cognitive biases. Yet there is no data of such models solving emotional intelligence (EI) tasks. They are connected to the abilities that has been previously considered as specifically human EI is an important aspect of human communication. The ability to understand and respond to emotional cues is essential for effective communication. Therefore, it is crucial to determine the ways AI models such as ChatGPT demonstrate EI. The present research aims to measure the EI of GPT-4, a large language model trained by OpenAI. Russian version of the Mayer–Salovey–Caruzo Emotional Intelligence Test sections B, C, D, F, G and H were used in this research. High points were obtained in Understanding emotions scale and Strategic EI. Mean points are obtained in Managing emotions scale. Low and less reliable values are obtained in Using emotions to facilitate thought scale. Thus, GPT-4 seems already capable of identifying emotions in text and describing techniques for managing them. However, complex cases and irregular situations requiring emotions qualitative analysis would be a hard task for GPT-4.

The dominance of social media has added to the channels of bullying to perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance issue and generalisation. In recent years, large language models (LLM) like BERT and RoBERTa have achieved state of the art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed RoBERTa outperformed other models.

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of this data present substantial challenges in data modeling and analysis, which have been tamed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of Large Language Models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and generation of human behavior through the lens of wearable sensor data. This survey explores current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensors data, the capabilities and limitations of LLMs to model them and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensors data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensors data and LLMs, offering insights into the current state and future prospects of this emerging field.

Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent Based Models and Simulation consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Agents generate large volumes of data over time and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents’ perspectives on key events by providing natural language narratives. However, these narratives need to be factual, transparent, and reproducible. To this end, we present a structured narrative prompt for sending queries to LLMs. Chi-square tests and Fisher’s Exact tests are applied to assess statistically significant difference in sentiment scores of the narrative messages between simulation generated narratives, ChatGPT-generated narratives, and real tweets. The narrative prompt structure effectively yields narratives with the desired components from ChatGPT. This structure is expected to be extensible across LLMs. In 14 out of 44 categories, ChatGPT generated narratives which has sentiment scores that were not discernibly different, in terms of statistical significance (alpha level of 0.05), from the sentiment expressed in real tweets. Three outcomes are provided: (1) a list of benefits and challenges for LLMs in narrative generation; (2) a structured prompt for requesting narratives of a LLM based on simulated agents’ information; and (3) an assessment of statistical significance in the sentiment prevalence of the generated narratives compared to real tweets. This indicates significant promise in the utilization of LLMs for helping to connect simulated agent’s experiences with real people.

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinizes the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs like GPT-4, GPT-3, and LLAMA, adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluate these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain accuracy, efficiency, and scalability. Our results reveal that while conventional models excel with structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

In this study, the on-going research into the improvement of micro-gas turbine propulsion system performance and the suitability for application as propulsion systems for small tactical UAVs (<600 kg) is investigated. The study is focused around the concept of converting existing micro turbojet engines to turbofan with the use of a continuously variable gearbox, thus maintaining a single spool configuration and relative design simplicity. This is an effort to reduce the initial engine development cost, whilst improving propulsive performance. The BMT 120 KS micro turbojet engine is selected for performance evaluation of the conversion process using gas turbine performance software, GasTurb13. The preliminary design of a matched low-pressure compressor (LPC) for the proposed engine is then performed using meanline calculation methods. According to the analysis carried out, an improvement in the converted micro gas turbine engine performance in terms of thrust and specific fuel consumption is achieved. Furthermore, with the introduction of a CVT gearbox, fan speed operation may be adjusted independently of the core, allowing increased thrust generation or better fuel consumption. Therefore, enabling a wider gamut of operating conditions and enhances the performance and scope of tactical UAV.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

Language models like BERT dominate current NLP research due to their robust performance, but they are vulnerable to backdoor attacks. Such attacks cause the model to consistently generate incorrect predictions when specific triggers are present in the input, while maintaining normal behavior on clean inputs. In this paper, we propose a straightforward data poisoning method targeting the BERT architecture. Our approach does not involve complex modifications to the model or its training process; instead, it relies solely on altering a small portion of the training data. By introducing simple perturbations into just 10% of the training dataset, we demonstrate the feasibility of injecting a backdoor into the model. Our experimental results show a high attack success rate, indicating that the model trained on the poisoned data can reliably associate the trigger with the attacker's desired outputs while its performance on clean data remains unaffected. This highlights the stealth and effectiveness of our method, emphasizing the need for improved defensive strategies to protect against such threats. Our study underscores the critical importance of ongoing research and development to safeguard AI systems from malicious exploitation, ensuring the security and reliability of NLP applications.

Pre-trained Language Models (PTLM) have remarkable and successful performance in solving lots of NLP tasks nowadays. And previous researchers have created many SOTA models and these models are included in many long surveys(Qiu et al., 2020). So, we would like to conduct a simple and short survey on this topic to help researchers understand the sketch of PTLM more quickly and comprehensively. In this short survey, we would provide a simple but comprehensive review of techniques, benchmarks, and methodologies in PTLM. And we would also introduce the applications evaluation of PTLM in this simple survey.

This paper discusses some of the most common misconceptions about large language models (LLMs), including the belief that they are sentient or conscious, that they are always accurate, and that they can replace human creativity. The paper also proposes a strategy for overcoming these misbeliefs, which involves educating the public about the capabilities and limitations of LLMs, developing guidelines for the responsible use of LLMs, and conducting more research to understand the potential impact of LLMs on society.

An artificial intelligence (AI)-based conversational large language model (LLM) was launched in November 2022 namely, “ChatGPT”. Despite the wide array of potential applications of LLMs in healthcare education, research and practice, several valid concerns were raised. The current systematic review aimed to investigate the possible utility of ChatGPT and to highlight its limitations in healthcare education, research and practice. Using the PRIMSA guidelines, a systematic search was conducted to retrieve English records in PubMed/MEDLINE and Google Scholar under the term “ChatGPT”. Eligibility criteria included the published research or preprints of any type that discussed ChatGPT in the context of healthcare education, research and practice. A total of 280 records were identified, and following full screening, a total of 60 records were eligible for inclusion. Benefits/applications of ChatGPT were cited in 51/60 (85.0%) records with the most common being the utility in scientific writing followed by benefits in healthcare research (efficient analysis of massive datasets, code generation and rapid concise literature reviews besides utility in drug discovery and development). Benefits in healthcare practice included cost saving, documentation, personalized medicine and improved health literacy. Concerns/possible risks of ChatGPT use were expressed in 58/60 (96.7%) records with the most common being the ethical issues including the risk of bias, plagiarism, copyright issues, transparency issues, legal issues, lack of originality, incorrect responses, limited knowledge, and inaccurate citations. Despite the promising applications of ChatGPT which can result in paradigm shifts in healthcare education, research and practice, the embrace of this application should be done with extreme caution. Specific applications of ChatGPT in health education include the promising utility in personalized learning tools and shift towards more focus on critical thinking and problem-based learning. In healthcare practice, ChatGPT can be valuable for streamlining the workflow and refining personalized medicine. Saving time for the focus on experimental design and enhancing research equity and versatility are the benefits in scientific research. Regarding authorship in scientific articles, as it currently stands, ChatGPT does not qualify to be listed as an author unless the ICJME/COPE guidelines are revised and amended. An initiative involving all stakeholders involved in healthcare education, research and practice is urgently needed to set a code of ethics and conduct on the responsible practices involving ChatGPT among other LLMs.

Large Language Models (LLMs) have revolutionized the field of Artificial Intelligence with their ability to understand and generate natural language discourse. This has led to the use of LLMs in various creative fields such as music, art, and storytelling, which has sparked a debate on the impact of LLMs on human creativity. This article explores the cyclic effect of LLMs on human creativity, where LLMs can generate an ever-evolving cycle of creative output from both humans and machines. The article also highlights the importance of responsible and ethical use of LLMs, including privacy and copyright issues with the training data used by LLMs. The article emphasizes the need for transparency, data security measures, and AI governance policies to protect user data and ensure the safe use of LLMs. It also calls for the development of educational materials and resources to increase public understanding of LLMs and their ethical implications. The article concludes by highlighting the potential of LLMs as powerful tools for communication and education, but also emphasizes the need for ethical considerations to ensure the responsible and beneficial use of LLMs in society.

The hump feature is one of the major instabilities in pump-turbines. When pump-turbines operate in the hump region, strong noise and serious fluctuations can be observed, which are harmful to their safe and stable operation and can even destroy the whole unit as well as water conveyance system. In this paper, a low specific speed (n_q = 36.1 min⁻¹) pump-turbine model was experimentally investigated. Firstly, the hump characteristic was obtained under 19 mm guide vane opening conditions. More interestingly, when the hump characteristic was measured in two directions (increasing and decreasing the discharge), characteristic hysteresis was found in the hump region. The analysis of performance characteristics reveals that the hump instability is the result of Euler momentum and hydraulic losses, and different Euler momentum and hydraulic losses in the two development processes lead to the hysteresis phenomenon. Then, 12 pressure sensors were mounted in the different parts of the pump-turbine model to obtain the time and frequency characteristics. The analysis of the corresponding fast Fourier transform confirms that the hump characteristic is related to low-frequency (0.04–0.15 times rotational frequency) vortices. The occurrence and cessation of vortices depend on the operating condition and measurement direction, which contribute to the hysteresis feature. Finally, the type of the low-frequency vortices was analyzed through the cross power spectrum.

In a trip planning service, travelers first set a starting point, a destination, and a sequential list of specific points of interest types (e.g., museums, restaurants, and parks). Based on this information, the service searches the spatial database to customize the best travel itinerary for the tourist. However, in previous studies, planners only considered the time factor when designing the optimal route, and failed to fully consider the quality of each point of interest. In this study, we specifically leveraged the capabilities of large language model to parse and respond to complex travel-related user queries. To apply large language model to route planning, we fine-tuned the model to understand geotagging and user travel preferences. We have introduced a novel graph search algorithm combined with large language model output, which optimizes the route search process to provide optimal travel recommendations by taking into account various factors such as distance length, budget constraints, and popularity of tourist attractions. In addition, we have integrated real-time traffic data and historical travel data to further improve the prediction accuracy and application usefulness of the model. In the experimental validation phase, we designed a series of benchmarks to compare the performance of the system with traditional algorithms and other machine learning-based route planning methods. Experimental results show that our model has a significant improvement compared with traditional methods in improving the speed and accuracy of path selection.

Good communication skills are essential for prospective workers, particularly college students, to clearly convey their abilities and understanding during job interviews. Despite the high demand for strong communication skills among employers, many students struggle with inadequate experience and skills, leading to reduced confidence and lower chances of securing desired jobs. Existing tools and resources for improving communication skills are limited, especially free ones, leaving students underprepared and less confident in interviews. To address this issue, a comprehensive solution is needed that provides free, customizable tools to enhance students' interview communication skills. Invisor is a web-based self-interview training application that leverages AI and Machine Learning to analyze users' behavior, responses, and facial expressions during simulated interviews. Accessible via desktop, laptop, or mobile devices, Invisor offers interactive and voice-recorded feedback to help students prepare for interviews effectively. By employing AI technologies, Invisor generates personalized interview questions based on job descriptions, enhancing the realism of the interview experience and providing tailored feedback to improve users' responses. Developed using agile methodologies, Invisor has undergone iterative enhancements, integrating user and stakeholder feedback promptly to improve usability and functionality. The combination of AI-driven simulations and agile development practices enables Invisor to meet current user needs and anticipate future demands, providing a robust tool for interview preparation in a competitive job market. This paper outlines the development and implementation of Invisor, demonstrating its effectiveness in enhancing interview skills and confidence among students and job seekers.

The growing dependence on large language models (LLM)s highlights the urgent need to deepen trust in these technologies. Regular, rigorous validation of their expertise, especially in nuanced and intricate scenarios, is essential to ensure their readiness for clinical applications. Our study pioneers the exploration of LLM utility in the field of cardiology. We stand at the cusp of a transformative era where mature AI and LLMs, notably ChatGPT, GPT-4, and Google Bard, are poised to influence healthcare significantly. Recently, we put three available LLMs, OpenAI's ChatGPT-3.5, GPT-4.0, and Google's Bard, to the test against a significant Polish medical special-ization licensing exam (PES). The exams cover the scope of completed specialist training, focusing on diagnostic and therapeutic procedures, excluding invasive medical procedures and interven-tions. In our analysis, GPT-4 consistently outperformed the others, ranking first, with and Google Bard and ChatGPT- 3.5 following, respectively. The performance metrics underscore GPT-4's no-table potential in medical applications. Given a score improvement of over 23.5 % between two AI models released just four months apart, clinicians must stay informed and up-to-date about these rapidly evolving tools and their potential applications to clinical practice. Our results provide a snapshot of the current capabilities of these models, highlighting the nuanced performance dif-ferences when confronted with identical questions

This retrospective study aimed to evaluate the performance of the hormone treatment protocols, determine the factors associated with pregnancy success after hormone treatment, and compare the cost-efficiencies of two types of hormone treatment among cyclic and noncyclic anestrous dairy cows. The clinical records of 279 anestrous cows who received hormone treatment for artificial insemination (AI) from 64 herds in the western region of Thailand were obtained from Kasetsart University Veterinary Teaching Hospital from January to August 2017. The performance of the hormone treatment protocols, fixed-time AI (TAI) and estrus detection before AI (EAI), showed that the pregnancy risk for the TAI protocol was higher than for the EAI protocol, but pregnancy per AI did not differ significantly between the two protocols in cyclic and noncyclic cows. Multivariate logistic regression analysis showed that cows receiving the TAI protocol were more likely to be pregnant compared to those treated with the EAI protocol. Cows with a 3.00 body condition score (BCS) &lt;3.75 after treatment and loose-housing cows were more likely to become pregnant. Treatment during winter showed higher pregnancy success than in the summer and rainy seasons. The cost-efficiency analysis showed that the TAI protocol was the most cost-efficient option for noncyclic cows, whereas the EAI protocol was the most cost-efficient option for cyclic cows.

Perceived peer support is a critical factor in the academic adjustment of higher vocational college students. While previous studies have explored this relationship, few studies have delved into the underlying mechanisms. This study surveyed 9782 students from 35 higher vocational colleges in 13 provinces and cities in China to explore the relationship and mechanisms between perceived peer support and academic adjustment. Drawing on Conservation of Resources theory and Social Support Resource theory, the findings revealed that perceived peer support not only directly predicted the academic adjustment of higher vocational college students, but also indirectly through the independent mediating effect of academic hope and professional identity, as well as the chain-mediating effect of academic hope to professional identity. Additionally, students from vocational high schools showed a more significant increase in academic hope due to perceived peer support compared to those from general high schools, highlighting the moderating effect of educational background. The study provided a new theoretical perspective for understanding the complex mechanisms of academic adjustment in students and offers valuable guidance for educational practice, emphasizing the importance of fostering perceived peer support, academic hope, and professional identity in higher vocational education.

Disaster issue consultation is crucial for effective emergency management, requiring timely and accurate information to support decision-making processes. This paper explores the integration of large language models (LLMs) with advanced prompt engineering to enhance the performance of AI systems in disaster management. We propose a novel multi-round prompt engineering approach that guides LLMs to iteratively refine their responses based on evolving disaster scenarios. Our method leverages diverse disaster-related datasets and employs a combination of accuracy metrics and a customized GPT-4 scoring system for evaluation. We conduct comprehensive experiments across multiple LLM platforms, including Qwen2, ChatGPT, Claude, and GPT-4, comparing our approach with baseline models and the Tree of Thoughts (ToT) method. The results demonstrate significant improvements in both accuracy and response quality, highlighting the effectiveness of our method in providing contextually relevant and actionable insights. Additional analysis confirms the robustness and generalizability of our approach across various disaster scenarios, establishing it as a valuable tool for enhancing disaster management practices.

The Dph1•Dph2 heterodimer from yeast is a radical SAM (RS) enzyme that generates the 3-amino-3-carboxy-propyl (ACP) precursor for diphthamide, a clinically relevant modification on eukaryotic elongation factor 2 (eEF2). ACP formation requires SAM cleavage and atypical Cys-bound Fe-S clusters in each Dph1 and Dph2 subunit. Intriguingly, the first Cys residue in each motif locates next to another, ill-defined cysteine that we show in-here is conserved across eukaryotes. As judged from structural modeling, the orientation of these tandem cysteine motifs (TCM) suggests a candidate Fe-S cluster ligand role. Hence, we generated by site-directed DPH1 and DPH2 mutagenesis, Dph1•Dph2 variants with cysteines from each TCM replaced individually or in combination by serines. Assays diagnostic for diphthamide formation in vivo reveal that while single substitutions in the TCM of Dph2 cause mild defects, double mutations almost entirely inactivate the RS enzyme. Based on enhanced Dph1 and Dph2 subunit instability in response to cycloheximide chases, the variants with Cys substitutions in their cofactor motifs are particularly prone to protein degradation. In sum, we identify a fourth functionally cooperative Cys residue within the Fe-S motif of Dph2 and show that the Cys-based cofactor binding motifs in Dph1 and Dph2 are critical for the structural integrity of the dimeric RS enzyme in vivo.

In the rapidly advancing field of Artificial Intelligence (AI), this study presents a critical evaluation of the resilience and cybersecurity efficacy of leading AI models, including ChatGPT-4, Bard, Claude, and Microsoft Copilot. Central to this research is the use of innovative adversarial prompts designed to rigorously test the content moderation capabilities of these AI systems. The study introduces new types of adversarial tests and the Response Quality Score (RQS), a metric specifically developed to assess the nuances of AI responses. Additionally, the research spotlights FreedomGPT, an AI tool engineered to optimize the alignment between user intent and AI interpretation. The empirical results from this investigation are pivotal for assessing the current robustness and security of AI models. They highlight the necessity for ongoing development and meticulous testing to bolster AI defenses against an array of adversarial challenges. Importantly, the study also delves into the ethical and societal implications associated with employing advanced 'jailbreak' techniques in AI testing. The findings are significant for understanding AI vulnerabilities and formulating strategies to enhance the reliability and ethical soundness of AI technologies, paving the way for safer and more secure AI applications.

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

This study presents a strategic approach to developing applications focused on implementing Large Language Models using the Langchain framework in Python. Three language models are highlighted: GPT-3.5 (turbo mode), LLaMA 2, and Vicuna 7B, each with their distinctive features and capabilities. The methodology used is described in detail, including data extraction from medical reports using zero-shot prompting data extraction techniques, interaction with language models, and structured storage of results. The performance of the models in data extraction is evaluated, presenting metrics such as precision, recall, and F1 score. The results demonstrate high model capability in extracting information, although areas for improvement are identified, particularly in data extraction precision. In conclusion, the efficacy of the models in extracting information from medical histories is not considerably acknowledged, with an emphasis on the importance of improving precision and increasing the volume of trained data for future research in healthcare digitalization.

The age-related loss of muscle mass and strength is referred to as “sarcopenia”. The combined effect of sarcopenia and osteoporosis is a devastating threat to the old adult, accounting for reduced mobility, risk for falls and subsequent fractures. In previous studies, we observed a high degree of inter-individual variability of paraspinal muscle fatty infiltration, one most relevant index of muscle wasting. This aspect solicited us to develop a computerized method to quantitatively characterize muscle fatty infiltration in aging and diseases. Magnetic resonance images of paraspinal muscles from 58 women of different age (age range 23-85 years) and physio-pathological status (healthy young, pre-menopause, post-menopause, and os-teoporosis), were used to set up the method. It is based on fractal analysis of lean muscle area (contractile muscle) to estimate muscle fatty infiltration. In particular, lacunarity was computed by parameter β from our hyperbola model function, used to fit the GBA (gliding box algorithm) curvilinear plot. Succolarity was estimated by parameter µ, for the four main directions, through an algorithm implemented on purpose. Results show that fractal lacunarity, by quantifying muscle fatty infiltration, can discriminate be-tween osteoporosis and healthy aging while succolarity can separate the other three groups showing similar lacunarity. Therefore, fractal features of contractile muscle, by measuring fatty infiltration, can represent good indices of sarcopenia in aging and disease.

Speech recognition, or automatic speech recognition (ASR), is a technology designed to convert spoken language into text using software. However, conventional ASR methods involve several distinct components, including language, acoustic, and pronunciation models with dictionaries. This modular approach can be time-consuming and may influence performance. In this study, we propose a method that streamlines the speech recognition process by incorporating a unified recurrent neural network (RNN) architecture. Our architecture integrates a convolutional neural network (CNN) with an RNN and employs a connectionist temporal classification (CTC) loss function. Key experiments were carried out using a dataset comprising 576,656 valid sentences, using erosion techniques. Evaluation of the model performance, measured by the word error rate (WER) metric, demonstrated remarkable results, achieving a WER of 2%. This approach has significant implications for the realm of speech recognition, as it alleviates the need for labor-intensive dictionary creation, enhancing the efficiency and accuracy of ASR systems, and making them more applicable to real-world scenarios. For future enhancements, we recommend the inclusion of dialectal and spontaneous data in the dataset to broaden the model's adaptability. Additionally, fine-tuning the model for specific tasks can optimize its performance for targeted objectives or domains, further enhancing its effectiveness in those areas.

Accurate crop diseases classification is crucial for ensuring food security and enhancing agricultural productivity. However, existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhances multimodal synergy for better crop disease classification than traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to using solely the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing prompt quality. Secondly, we integrate the cross-attention and the SE (Squeeze-and-Excitation) attention into the training-free mode VLCD (Vision-Language model for Crop Diseases classification) and the training-required mode VLCD-T (VLCD-Training) respectively for prompt text processing, enhancing classifier weights by emphasizing key text features. Experimental outcomes conclusively prove our method’s heightened classification effectiveness in few-shot crop disease scenarios, tackling data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

Kinetic modeling is an essential tool in systems biology research, enabling the quantitative analysis of biological systems and predicting their behavior. However, the development of kinetic models is a complex and time-consuming process. In this article, we propose a novel approach called KinModGPT, which generates kinetic models directly from natural language text. KinModGPT employs GPT-3 as a natural language interpreter and Tellurium as an SBML generator. We demonstrate the effectiveness of KinModGPT in creating SBML models from complex natural language descriptions of biochemical reactions. KinModGPT successfully generates valid SBML models from a range of natural language model descriptions of metabolic pathways, protein-protein interaction networks, and heat shock response. This article demonstrates the potential of KinModGPT in kinetic modeling automation.

The article obtains large deviation asymptotic for sub-critical communication networks modelled as signal-interference-noise-ratio(SINR) random networks. To achieve this, we define the empirical power measure and the empirical connectivity measure, as well as prove joint large deviation principles(LDPs) for the two empirical measures on two different scales. Using the joint LDPs, we prove an Asymptotic equipartition property(AEP) for wireless telecommunication Networks modelled as the subcritical SINR random networks. Further, we prove a Local Large deviation principle(LLDP) for the sub-critical SINR random network. From the LLDPs, we prove the large deviation principle, and a classical McMillan Theorem for the stochastic SINR model processes. Note that, the LDPs for the empirical measures of this stochastic SINR random network model were derived on spaces of measures equipped with the $\tau-$ topology, and the LLDPs were deduced in the space of SINR model process without any topological limitations. We motivate the study by describing a possible anomaly detection test for SINR random networks.

This paper represents a groundbreaking paradigm shift in network optimization. Departing from traditional static methodologies, this innovative approach harnesses the power of Generative Artificial Intelligence (AI) and Large Language Models (LLMs) to optimize cloud networks dynamically. By integrating advanced AI algorithms, this framework continuously adapts and evolves, ensuring optimal real-time performance. This dynamic optimization enhances efficiency and resilience, allowing cloud networks to adjust seamlessly to changing demands and conditions. Through the fusion of cutting-edge technology and adaptive intelligence, this approach heralds a new era in network optimization, empowering organizations to achieve unprecedent-ed levels of agility and scalability in their cloud infrastructures.

Self-sustained learning (SSL) is considered a crucial factor in promoting students’ long-term learning and development in a sustainable society. To deepen the understanding of SSL, especially in the context of learning English as a second language, the current study examined the influence of intercultural communicative skills, language mindset, and positive L2 self on SSL in English learning among 1,238 college students in China. The results showed that students not only had a strong language mindset, positive L2 self, and intercultural communicative skills but also scored higher in long-term self-sustained English learning. Findings from the Structural Equation Modeling indicated that both language mindset and intercultural communicative skills positively predicted positive L2 self and self-sustained English learning. Furthermore, language mindset and intercultural communicative skills had an indirect impact on self-sustained English learning through positive L2 self. These findings suggest that to promote English learners’ SSL, instructors should help facilitate students’ intercultural communicative skills and foster a growth language mindset, as well as positive language learning beliefs.

Large language models have proliferated across multiple domains in as short period of time. There is however hesitation in the medical and healthcare domain towards their adoption because of issues like factuality, coherence, and hallucinations. Give the high stakes nature of healthcare, many researchers have even cautioned against its usage until these issues are resolved. The key to the implementation and deployment of LLMs in healthcare is to make these models trustworthy, transparent (as much possible) and explainable. In this paper we describe the key elements in creating reliable, trustworthy, and unbiased models as a necessary condition for their adoption in healthcare. Specifically we focus on the quantification, validation, and mitigation of hallucinations in the context in healthcare. Lastly, we discuss how the future of LLMs in healthcare may look like.

Humans have a unique cognitive ability known as relational abstraction, which allows us to identify logical rules and patterns beyond basic perceptual characteristics. This ability represents a key difference between how humans and other animals learn and interact with the world. With current large language models rivaling human intelligence in many regards, we investigated whether relational abstraction was an emergent chat completion capacity in various models. We find that despite their impressive language processing skills, all tested language models failed the relational match-to-sample (RMTS) test, a benchmark for assessing relational abstraction. These results challenge the assumption that advanced language skills inherently confer the capacity for complex relational reasoning. The paper highlights the need for a broader evaluation of AI cognitive abilities, emphasizing that language proficiency alone may not be indicative of certain higher-order cognitive processes thought to be supported by language.

In recent times, BERT based transformer models have become an inseparable part of the 'tech stack' of text processing models. Similar progress is being observed in the speech domain with a multitude of models observing state-of-the-art results by using audio transformer models to encode speech. This begs the question of what are these audio transformer models learning. Moreover, although the standard methodology is to choose the last layer embedding for any downstream task, but is it the optimal choice? We try to answer these questions for the two recent audio transformer models, Mockingjay and wave2vec2.0. We compare them on a comprehensive set of language delivery and structure features including audio, fluency and pronunciation features. Additionally, we probe the audio models' understanding of textual surface, syntax, and semantic features and compare them to BERT. We do this over exhaustive settings for native, non-native, synthetic, read and spontaneous speech datasets

Large language model (LLM) is a representation of a major advancement in AI, and has been used in multiple natural language processing tasks. Nevertheless, in different business scenarios, LLM requires fine-tuning by engineers to achieve satisfactory performance, and the cost of achieving target performance and fine-tuning may not match. Based on the Baidu STI dataset, we study the upper bound of the performance that classical information retrieval methods can achieve under a specific business, and compare it with the cost and performance of the participating team based on LLM. This paper gives an insight into the potential of classical computational linguistics algorithms, and which can help decision-makers make reasonable choices for LLM and low-cost methods in business R&D.

Buildings have started to play a critical role in the stability and resilience of modern smart grids, leading to a refocusing of large scale energy management strategies from the supply side to the consumer side. When the buildings integrate local renewable energy generation in the form of renewable energy resources they become prosumers and this reflects into additional complexity into the operation of the interconnected complex energy systems. A class of methods of modelling the energy consumption patterns of the building have recently emerged as black-box input-output approaches with the ability to capture underlying consumption trends. These make use and require large quantities of quality data produces by non-deterministic processes underlying the energy consumption. We present an application of a class of neural networks, namely deep learning techniques for time series sequence modelling with the goal of accurate and reliable building energy load forecasting. The Recurrent Neural Network implementation uses Long Short-Term Memory layers in increasing density of nodes to quantify prediction accuracy. The case study is illustrated on four university buildings from temperate climates over one year of operation using a reference benchmarking dataset that allows replicable results. The obtained results are discussed in terms of accuracy metrics and computational and network architecture aspects and are considered suitable for further used in future in situ energy management at the building and neighbourhood levels.

A variable annuity is a popular life insurance product that comes with financial guarantees. Using Monte Carlo simulation to value a large variable annuity portfolio is extremely time-consuming. Metamodeling approaches have been proposed in the literature to speed up the valuation process. In metamodeling, a metamodel is first fitted to a small number of variable annuity contracts and then used to predict the values of all other contracts. However, metamodels that have been investigated in the literature are sophisticated predictive models. In this paper, we investigate the use of linear regression models with interaction effects for the valuation of large variable annuity portfolios. Our numerical results show that linear regression models with interactions are able to produce accurate predictions and can be useful additions to the toolbox of metamodels that insurance companies can use to speed up the valuation of large VA portfolios.

The development of plant-based meat analogues has become a significant challenge for the food industry in recent years due to the increasing demand for sustainable and healthier proteins in the context of a global protein transition. Plant-based meat analogues imitate the visual, textural, and chemical properties of traditional meat products and are required to closely resemble meat to appeal to consumers. In addition, consumers demand natural, clean-label, and nutritional and healthy products. To address these challenges, the food industry must develop highly healthy, nutritious, and E-number-free meat analogue products. Understanding the functionality of each ingredient and its role in the food matrix is crucial to being a key player in the innovation of the meat analogues market. This review provides updated information on the primary ingredients utilized for the development of plant-based burger meat alternatives and their functionality. The key components of meat analogue burgers are outlined, including plant proteins, binding agents, fats and oils, flavorings, colorings, preservatives, fortificants, and clean-label considerations.

This paper presents our approaches for the SMM4H’24 Shared Task 5 on the binary classification of English tweets reporting children’s medical disorders. Our first approach involves fine-tuning a single RoBERTa-large model, while the second approach entails ensembling the results of three fine-tuned BERTweet-large models. We demonstrate that although both approaches exhibit identical performance on validation data, the BERTweet-large ensemble excels on test data. Our best-performing system achieves an F1-score of 0.938 on test data, outperforming the benchmark classifier by 1.18%.

Artificial intelligence (AI) driven language models have seen a rapid rise in development, deployment, and adoption over the last few years. This surge has sparked many discussions about their societal and political impact, including political bias. Bias is a crucial topic in the context of large models due to its far-reaching consequences on technology, politics, and society. It significantly influences public perception, decision-making, political discourse, and AI policy governance and ethics. This study investigates political bias through a comparative analysis of four prominent AI models: ChatGPT-4, Perplexity, Google Gemini, and Claude.Through a comprehensive analysis by systematically and categorically evaluating their responses to politically and ideologically charged tests and prompts, utilizing the Pew Research Center’s Political Typology Quiz, the Political Compass assessment, and ISideWith political party quiz, this study identifies significant ideological leanings and the nature of political bias within these models. The findings revealed that ChatGPT-4 and Claude exhibit a liberal bias, Perplexity is more conservative, while Google Gemini adopts more centrist stances. The presence of such biases underscores the critical need for transparency in AI development and the incorporation of diverse training datasets, regular audits, and user education to mitigate these biases. This analysis also advocates for more robust practices and comprehensive frameworks to assess and reduce political bias in AI, ensuring these technologies contribute positively to society and support informed, balanced, and inclusive public discourse, which will point towards neutrality.The results of this study add to the ongoing discourse about the ethical implications and development of AI models, highlighting the critical need to build trust and integrity in AI models. Additionally, future research directions have been outlined to explore and address the complex issue of bias in AI.

Software systems are often maintained by a group of experienced software developers, in order to ensure that faults which may bring the system down are less likely. Large turnover in organizations such as CERN makes it important to think of ways of onboarding newcomers on a technical project rapidly. This paper focuses on optimizing the way that people get up-to-speed on the business logic and technologies used on the project, using a knowledge-imbued large language model that is enhanced using domain-specific knowledge from the group or team’s internal documentation.

This paper explores the role of open-source large language models in IoT cybersecurity world. The threats of malicious activity on the Internet and the loss of private information are very real and lead to serious consequences. The purpose of this paper is to investigate how open source-large language models can help to defend against the growing threat of cyber-crimes. We conducted our experiments in two directions. The first one is a security assistant that helps with cybersecurity best practices advices. The second one is a how large language model can simulate a vulnerable IoT system. For both types of experiments, the interactive mode of operation of the language model is used. In the context of the cybersecurity research, a major advantage of the locally installed open-sourced large language models is that they do not share sensitive data with a remote system in a cloud. The paper concludes by discussing the potential impact of open-source large language models on cybersecurity research and recommends future research directions.

Sentiment analysis has become an important tool for understanding public opinion across languages and domains. Recently, there has been an increase in the number of studies on sentiment analysis in low-resource languages such as Kazakh. This is important to ensure that modern text analysis technologies are accessible to all users, regardless of their language background. The aim of the study is to create a sentiment analysis model for analyzing texts in Kazakh. As part of this work, we aim to use fine-tuning techniques on our own dataset for already existing models, thus improving their accuracy and efficiency for analyzing Kazakh language texts. This paper presents a manually collected dataset "KazIntTelCom" from the city information service 2GIS, consisting of user reviews, manually annotated by the authors taking into account the polarity of sentiment (i.e. negative positive or neutral). This dataset was used to fine-tune two pre-trained multi-lingual Transformer-based sentiment analysis models taken from the HuggingFace platform. The distillBERT and XLM-RoBERTa models were used for tuning. Also, the models were tested on the dataset "KazSAnDRA". The results show that accurate tuning even on a relatively small dataset gives a significant increase in performance, which is confirmed by an increase in the accuracy index by 20%-30%. In addition, false misses and false detections are analyzed, which allows us to identify directions for further improvement of the models. The contribution of this work, in addition to the dataset, is the analysis of model errors, which will help future developers to make more accurate settings of hyperparameters of training for sentiment analysis in Kazakh. These results are important for natural language processing and their adaptation to low-resource languages, promoting more inclusive and equitable access to modern analytical tools. Thus, this study demonstrates the effectiveness of the Transformers architecture for sentiment analysis in Kazakh and opens new opportunities for further model improvement.

Fluctuations of protein three-dimensional structures and large-scale conformational transitions are crucial for the biological function of proteins and their complexes. Experimental studies of such phenomena remain very challenging and therefore molecular modeling can be a good alternative or a valuable supporting tool for the investigation of large molecular systems and long-time events. In this mini-review, we present two alternative approaches to the coarse-grained (CG) modeling of dynamic properties of protein systems. We discuss two CG representations of polypeptide chains used for Monte Carlo dynamics simulations of protein local dynamics and conformational transitions and, on other hand, highly simplified structure-based Elastic Network Models of protein flexibility. In contrast to classical Molecular Dynamics the modeling strategies discussed here allow quite accurate modeling of much larger systems and longer time dynamic phenomena. We briefly describe the main features of these models and outline some of their applications, including modeling of near-native structure fluctuations, sampling of large regions of the protein conformational space, or possible support for the structure prediction of large proteins and their complexes.

This research presents the Cross-Cultural Intelligent Language Learning System (CILS), a novel approach integrating Artificial Intelligence (AI) into language education to enhance cross-cultural communication. CILS utilizes advanced AI technologies to provide adaptive, personalized learning experiences that cater to the unique linguistic and cultural backgrounds of each learner. By dynamically adjusting content and methodology, CILS significantly improves linguistic proficiency and cultural understanding, essential for effective global interactions. The implementation of CILS in platforms such as Busuu and HelloTalk has demonstrated marked improvements in engagement and communication skills among learners. Empirical studies validate the system's effectiveness in real-world settings, showing enhanced learner performance and increased intercultural competence. Additionally, the Technology Acceptance Model (TAM) applied confirms that the usability and perceived usefulness of AI-driven systems strongly influence learner acceptance and sustained use. This study not only underscores the potential of AI in transforming language education but also highlights the critical role of cultural sensitivity in designing educational technologies.

Sixteen crossbred rabbits (New Zealand white x Thai native breed) were randomly divided into two groups of eight to determine the effects of daily oral administration of crude extracts from the butterfly pea (Clitoria ternatea L.) from weaning (at 35 days) to slaughter (at 90 days). Effects on phagocytic activity of blood polymorphoneuclear leukocytes, serum biochemistry, meat quality, muscular lipid peroxidation, apparent digestibility, and gut histology were studied. The results revealed that the phagocytic function of circulating leukocytes (75 and 90 days) and alveolar macrophages (90 days) did not differ between the two groups. At slaughter, treated rabbits had lower blood urea nitrogen concentrations and higher liver weight than control rabbits (p &lt; 0.05). After chilling at 4°C for 24 hours, lower meat pH and alteration of meat color (a brighter, less yellow, Hue angle and color saturation) were observed in the treated group (p &lt; 0.05). Furthermore, lipid peroxidation (measured at 3, 5 and 7 storage days) in the meat of treated rabbits was lower than in controls (p &lt; 0.05). Apparent digestibility (analyzed at 46 days for four days) revealed improved organic matter and ether extracts in the treated group (p &lt; 0.05), whereas gut histology was unaffected. In conclusion, butterfly pea extract supplementation did not affect phagocytic function but led to a modification in meat color, delayed lipid peroxidation, and improved digestibility.

To conduct high-precision and high-resolution numerical simulation of complex flow structures in turbomachinery, a high-order finite volume weighted essentially non-oscillatory (WENO) scheme for the large eddy simulation (LES) is improved and embedded into the three-dimensional viscous unsteady CFD solver NUAA-Turbo. Firstly, the spectral characteristics and unsteady convergence of the improved WENO scheme are studied. Compared with the classical WENO scheme, the improved WENO scheme has better dissipation and dispersion characteristics and faster convergence speed. Then, the coefficient CW of the Wall-Adapting Local Eddy-viscosity (WALE) model is calibrated by decaying homogeneous isotropic turbulence (DHIT) test case. Finally, the scheme is applied to conduct high-precision LES calculations of turbulent boundary layer flow, supersonic compression corner flow, and low-pressure turbine cascade separation flow. The numerical simulation results show that this WENO scheme has excellent shock wave capture ability and turbulence resolution and can capture more flow field details with less mesh size, greatly reducing the computational cost and laying a foundation for large-scale engineering application of LES.

Tao and Ming (name) or Tao and Yan (language or speech) is an inseparable pair of important concepts in traditional Chinese language philosophy. In LaoTze’s opinion, Tao could not be spoken out, and language or speech could not reach Tao’s essence. Yan and Tao are separated from each other, and they are paradoxical. All the confusion derives from Yan regardless of how delicate they are. Tao can be expressed in words, but it will never be expressed through common languages. In this article, Tao is regarded as a human being’s thoughts or intentions and is even considered to be the origin of the real world. Language can express people’s thought, although it has some limitations. There exist some contradictions between the real word and the world expressed in words. To enable people to better understand the existence of the real world from multiple perspectives at the language or linguistic level without being constrained by words, this article studies LaoTze’s linguistic philosophy reflected in his opinion on the relationship between Tao and Yan and makes a comparative analysis of modern Western language philosophers’ stand on language (or speech) and existence.

This study introduces an innovative seeding method for cells on large scaffolds (1-100 sqcm) with an accuracy of 0.1mm, comparing the conventional drop-wise seeding technique with an automated seeding approach using an open sourced robotic liquid handling system (OpenLH). This automated system employs an algorithm in which the user inputs the desired droplet volume and seeding pattern dimensions such in number of rows, columns and distance between droplets, thus optimizing the distribution of cells on the scaffold. By adjusting these parameters, the method achieves greater accuracy and consistency over manual seeding and requires less operation space volume than dynamic seeding. Additionally, the system’s tip replacement feature can support the precise seeding of multiple cell types on a single scaffold and the dispensing of growth factors to foster patterns of cell differentiation and proliferation on the large 3D scaffold. This seeding method not only enhances the precision and efficiency of cell distribution on scaffolds but also shows significant potential for scalability in the cultured meat industry, where large scaffolds are essential. The adoption of such automated systems could promote efficient scaffold-based tissue engineering by promoting uniform cell distribution and enabling the creation of complex tissue constructs, thereby advancing both biomedical research and cultured meat production.

We hypothesis that large earthquakes generate Horndeski-like Gravitational Wave (GW). We find that such a Horndeski-like GW propagates with the speed of sound. The sound waves generated by an earthquake make a local and temporal change to the Earth’s diagravitational medium; therefore, they modify the GW speed in a standard, Alternative-Theory-of-Gravity (ATG) sense. The quantum of the Horndeski-like GW is a massless scalar quasiparticle and cannot exist outside of the propagation region of the P-field. The Horndeski-like GW may be detectable by future GW detectors with a sensitivity of 10−15 Hz^−1/2 in the region of 0.1–1 Hz.

Subgrid scale models for unresolved turbulent fluxes are investigated with a focus on combustion for space propulsion applications. An extension to the gradient model is proposed, introducing a dependency on the local burning regime. The dynamic behavior of the model's coefficients is investigated, and scaling laws are studied. The discussed models are validated using a DNS database of a high-pressure turbulent fuel-rich methane-oxygen diffusion flame. The operating point and turbulence characteristics are selected to resemble those of modern combustors for space propulsion applications to support the future usage of the devised model in this context.

Large lithium-ion batteries (LIBs) in electric vehicles and energy storage systems demonstrate different performance and lifetime compared to small LIB cells, owing to the size effects generated by the electrical configuration and property imbalance. However, the calculation time for performing life predictions with three-dimensional (3D) cell models is undesirably long. In this paper, a lumped cell model with equivalent resistances (LER cell model) is proposed as a reduced order model of the 3D cell model, which enables accurate and fast life predictions of large LIBs. The developed LER cell model is validated via the comparisons with results of the 3D cell models by simulating a 20-Ah commercial pouch cell (NCM/graphite) and the experimental values. In addition, the LER cell models are applied to different cell types and sizes, such as a 20-Ah cylindrical cell and a 60-Ah pouch cell.

External hoof characteristics, balance, and conformation have been extensively studied in horses; however, mules remain understudied in these aspects. This study evaluated the size, shape, and symmetry of untrimmed and unshod forelimb hooves, compared the symmetry between forelimb hooves and stratified external forelimb hoof measurements based on the body condition score of mules raised in the foothill plains of northern Thailand. The forelimb hooves of 38 mules were photographed and 33 parameters, including angular and linear measurements, were analyzed. Despite the absence of shoeing and trimming, these mules exhibited optimal left-right forelimb hoof symmetry, with no significant (p < 0.05) differences in: outer wall length and inner wall length (OWL - IWL); sole length and sole width (SLS - SW); dorsal hoof wall length and heel length (DHWL - HL); and frog length and frog width (FL - FW). However, significant (p < 0.05) differences were observed within each body condition score group for forelimb hoof measurements for DHWL, IWL, heel separation (HS), heel bulb distance (HBD), SW, FW, and FL. These findings provide valuable insights into mule welfare and management, contributing to understanding of the interplay between overall health and hoof conformation in the study area.

Biofuels and biochemicals play significant roles in the transition towards a fossil-free society. However, large-scale biorefineries are not yet cost-competitive with their fossil-fuel counterparts, and it is important to identify biorefinery concepts with high economic performance. For evaluating early-stage biorefinery concepts, one needs to consider not only the technical performance and process costs but also the economic performance of the full supply chain and the impacts on feedstock and product markets. This article presents and demonstrates a conceptual interdisciplinary framework that can constitute the basis for evaluations of the full supply-chain performance of biorefinery concepts. This framework considers the competition for biomass across sectors, assumes exogenous end-use product demand, and incorporates various geographical and technical constraints. The framework is demonstrated empirically through a case study of a sawmill-integrated biorefinery producing liquefied biomethane from forestry and forest industry residues. The case study results illustrate that acknowledging biomass market effects in the supply chain evaluation implies changes in both biomass prices and the allocation of biomass across sectors. The proposed framework should facilitate the identification of biorefinery concepts with a high economic performance which are robust to feedstock price changes caused by the increase in biomass demand.

In this paper, we studied the problem of early detection of natural phenomena associated with the formation of severe floods and the possibility of constant monitoring of their occurrence. The test object for the study was severe floods on the Crimean Peninsula, which occurred due to heavy rainfall in the summer of 2021. Based on the selected satellite and other data related to this period, an analysis carried out and key atmospheric objects identified, according to the proposed algorithm for their identification and grouping. Based on the results of the work, a positive conclusion made on the issue of their use to identify the likelihood of natural disasters that could lead to floods. In addition, the authors proposed to develop a portal for collecting and processing a large amount of satellite data related to flood prevention and monitoring the development of such processes, and stressed the need to create it.

The attitude dynamics and orbit dynamics of large rigid space structures are coupled with each other under gravity gradient, which may affect the stability of the large rigid space structures. In this paper, the gravity gradient stability of a large rigid space structure is studied under both small and large disturbances. Based on the rigid body dynamics and orbit dynamics, an accurate dynamic model without any linearization of the large rigid space structure is established via the natural coordinate formulation (NCF), which is able to describe the large overall motions of the structures. By using the generalized-α algorithm, the gravity gradient stability of the large rigid space structure is simulated and analyzed via various examples, including the influence of large disturbance angles, the positions at the stabilization and unstabilization regions. Finally, the relationship between spinning stability and gravity gradient stability is also investigated via a large spinning space structure.

In this paper, we first discuss the research status and application progress of the finite element method and the smoothed particle method. By analyzing the advantages of the smoothed particle method and the finite element method, a new coupling algorithm, namely FEM-SPH algorithm, is proposed. By the method of comparison, it shows that finite element method and SPH method in the simulation of large deformation problems each have advantages and disadvantages, the finite element method smoothed particle coupling algorithm is effective to achieve the performance of high computational efficiency and can naturally simulate large deformation problems across. In the process of calculation, the large deformation unit can be freely into an algorithm to facilitate the calculation accuracy and efficiency of three methods of numerical simulation. Through the study found, FEM-SPH algorithm not only overcome the defect of smooth particle tensile instability, but also overcomes the problem of low efficiency of finite element computation. To further test the FEM-SPH algorithm has advantages in the practical engineering, we have carried out the actual test to the example of the super high speed collision, concluded that, since the target of most of the computational domain is always finite element, smoothed particle focused only in contact with the projectile and target of local area, particle number is not much, the whole calculation process just ten minutes, computational efficiency has been greatly improved, at the same time in the simulation of large deformation, the advantage is very obvious .This provides a criterion for the actual project, depending on the specific material deformation mode and choose a more appropriate conversion algorithm.