Version 1
: Received: 8 May 2024 / Approved: 10 May 2024 / Online: 13 May 2024 (08:11:44 CEST)
How to cite:
Cohen, Y.; Aperstein, Y. A Review of Generative Pretrained Multi-step Prompting Schemes –and a New Multi-step Prompting Framework. Preprints2024, 2024050720. https://doi.org/10.20944/preprints202405.0720.v1
Cohen, Y.; Aperstein, Y. A Review of Generative Pretrained Multi-step Prompting Schemes –and a New Multi-step Prompting Framework. Preprints 2024, 2024050720. https://doi.org/10.20944/preprints202405.0720.v1
Cohen, Y.; Aperstein, Y. A Review of Generative Pretrained Multi-step Prompting Schemes –and a New Multi-step Prompting Framework. Preprints2024, 2024050720. https://doi.org/10.20944/preprints202405.0720.v1
APA Style
Cohen, Y., & Aperstein, Y. (2024). A Review of Generative Pretrained Multi-step Prompting Schemes –and a New Multi-step Prompting Framework. Preprints. https://doi.org/10.20944/preprints202405.0720.v1
Chicago/Turabian Style
Cohen, Y. and Yehudit Aperstein. 2024 "A Review of Generative Pretrained Multi-step Prompting Schemes –and a New Multi-step Prompting Framework" Preprints. https://doi.org/10.20944/preprints202405.0720.v1
Abstract
This paper reviews the pioneering work related to the generation of a sequence of prompts in Pretrained Language Models (PLMs) to automatically complete a complex writing task. The paper identifies the main categories of automated multi-step prompting and discusses their advantages and disadvantages. The paper also proposes an additional approach for automated multi-step prompting with iterative four main phases: in the first phase a sequence of prompts is geared to elicit the structure of the requested task. This is done by identifying the task’s main parts, the general contents of the different parts and their precedence relations. The structure of each main part is iteratively explored to find secondary and tertiary parts if they exist. A second phase is followed by a sequence of prompts that fill in the primary, secondary, and tertiary parts, and seek to fine-tune the result. The third phase reviews the generated text and criticizes it. Based on this criticism a revision is prepared. The fourth phase is fine-tuning the document, with emphasis on section length and text tone. Future research could deal with the system identification of points where the system should initiate interaction with the user for desired feedback and guidance.
Keywords
Iterative prompting, sequential prompting, recursive prompting, prompt engineering, adaptive prompting, chain of thought
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.