Download pdf
GPThelper: A Prompt That You Can Discover LLM’s Full Potential
- 1 Nanjing University of Posts and Telecommunications
* Author to whom correspondence should be addressed.
Abstract
It is widely acknowledged that LLMs(Large Language Models)assist us in our daily lives and it both save our times and energy,but it still fails in some specific area like DSL(Domain Specific Language). In response to this, the GPThelper was invented, which includes basic knowledge of the language, concepts, and commands used by the language, as well as tips for improvement to correct mistakes.With the Brainf language, issues were first identified in the program calculator regarding the location of the pointer, and prompts were improved to correct this. In the second experiment, errors occurred during the final section where parameters were to be added together, and these were subsequently corrected.In the evaluation section, various LLMs, including Kimi and Doubao, were tested using the GPThelper to handle tasks involving DSLs, and the results were excellent.It was found that this model works well with most LLMs, although there are still specific occasions where it fails.
Keywords
DSL,LLMs,Prompts
[1]. Feng Z, Guo D, Tang D, Duan N, Feng X, Gong M, Shou L, Qin B, Liu T, Jiang D et al. 2020 arXiv preprint arXiv:2002.08155
[2]. Brown T B 2020 arXiv preprint arXiv:2005.14165
[3]. Hadi M U, Al Tashi Q, Shah A, Qureshi R, Muneer A, Irfan M, Zafar A, Shaikh M B, Akhtar N, Wu J et al. 2024 Authorea Preprints
[4]. Gu X, Chen M, Lin Y, Hu Y, Zhang H, Wan C, Wei Z, Xu Y and Wang J 2024 ACM Transactions on Software Engineering and Methodology
[5]. Netz L, Reimar J and Rumpe B 2024 arXiv preprint arXiv:2407.06146
[6]. Bassamzadeh N and Methani C 2024 arXiv preprint arXiv:2407.02742
[7]. Mateas M 2008 Software Studies\A lexicon. London: MIT 267–276
[8]. Jun S W2016 Computer Science and AI Laboratory, MIT
[9]. Devlin J 2018 arXiv preprint arXiv:1810.04805
[10]. Yenduri G, Ramalingam M, Selvi G C, Supriya Y, Srivastava G, Maddikunta P K R, Raj G D, Jhaveri R H, Prabadevi B, Wang Wetal. 2024 IEEE Access
[11]. Fowler M 2010 Domain-specific languages (Pearson Education)
[12]. Williams K, McCandless J and Gregg D 2010 Dynamic interpretation for dynamic scripting languages Proceedings of the 8th annual IEEE/ACM international symposium on Code generation and optimization pp 278–287
[13]. Chen M, Tworek J, Jun H, Yuan Q, Pinto H P D O, Kaplan J, Edwards H, Burda Y, Joseph N, Brockman G et al. 2021 arXiv preprint arXiv:2107.03374
[14]. Ouh E L, Gan BKS,Jin Shim KandWlodkowski S 2023 Chatgpt, can you generate solutions for my coding exercises? an evaluation on its effectiveness in an undergraduate java programming course. Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1 pp 54–60
[15]. Coello C E A, Alimam M N and Kouatly R 2024 Digital 4 114–125
Cite this article
Han,P. (2025). GPThelper: A Prompt That You Can Discover LLM’s Full Potential. Applied and Computational Engineering,131,279-286.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Machine Learning and Automation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).