research-article
- Authors:
- Jaykumar Kasundra Thomson Reuters, IN
- Shreyans Dhankhar Thomson Reuters, IN
AIMLSystems '23: Proceedings of the Third International Conference on AI-ML SystemsOctober 2023Article No.: 32Pages 1–8https://doi.org/10.1145/3639856.3639888
- 0citation
- 0
- Downloads
Metrics
Total Citations0Total Downloads0Last 12 Months0
Last 6 weeks0
- Get Citation Alerts
New Citation Alert added!
This alert has been successfully added and will be sent to:
You will be notified whenever a record that you have chosen has been cited.
To manage your alert preferences, click on the button below.
Manage my Alerts
New Citation Alert!
Please log in to your account
- Publisher Site
- Get Access
AIMLSystems '23: Proceedings of the Third International Conference on AI-ML Systems
Adapting Open-Source LLMs for Contract Drafting and Analyzing Multi-Role vs. Single-Role Behavior of ChatGPT for Synthetic Data Generation
Pages 1–8
PreviousChapterNextChapter
ABSTRACT
Large-scale language models, such as ChatGPT[3] and GPT-4[32], have demonstrated remarkable capabilities in generating human-like text for various applications. In this paper, we focus on two key aspects: (1) adapting open-source large language models (LLMs) for specific use cases like contract drafting using instruction tuning and parameter-efficient fine-tuning, and (2) analyzing the difference in ChatGPT’s behavior in single-role prompts compared to multi-role prompts for synthetic data generation tasks. We present a method for aligning open-source LLMs to follow instructions for customized contract drafting scenarios using parameter-efficient fine-tuning on synthetic data. Furthermore, we investigate the data quality of the synthetically generated instructions data by ChatGPT with single-role vs. multi-role prompts. Our findings reveal that the model performs better when given single-role prompts, highlighting the importance of strategically designing prompting strategy to generate better quality data using LLMs. By combining the insights from these two aspects, we explore potential implications and opportunities for enhancing generative AI solutions for practical implementations. The Contract Drafting model 1 and data 2 are released.
References
- 2023. bitsandbytes slow inference issue. https://github.com/TimDettmers/bitsandbytes/issues/388.Google Scholar
- 2023. GitHub - databrickslabs/dolly: Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform — github.com. https://github.com/databrickslabs/dolly.Google Scholar
- 2023. Introducing ChatGPT — openai.com. https://openai.com/blog/chatgpt.Google Scholar
- 2023. NousResearch/Nous-Hermes-13b. https://huggingface.co/NousResearch/Nous-Hermes-13b.Google Scholar
- Vinay Aggarwal, Aparna Garimella, BalajiVasan Srinivasan, Rajiv Jain, 2021. CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring. arXiv preprint arXiv:2110.15794 (2021).Google Scholar
- StephenH Bach, Victor Sanh, Zheng-Xin Yong, Albert Webson, Colin Raffel, NihalV Nayak, Abheesht Sharma, Taewoon Kim, MSaiful Bari, Thibault Fevry, 2022. Promptsource: An integrated development environment and repository for natural language prompts. arXiv preprint arXiv:2202.01279 (2022).Google Scholar
- Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, 2022. Constitutional ai: Harmlessness from ai feedback. arXiv preprint arXiv:2212.08073 (2022).Google Scholar
- Łukasz Borchmann, Dawid Wiśniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Łukasz Szałkiewicz, Gabriela Pałka, Karol Kaczmarek, Agnieszka Kaliska, and Filip Graliński. 2019. Contract discovery: Dataset and a few-shot semantic retrieval challenge with competitive baselines. arXiv preprint arXiv:1911.03911 (2019).Google Scholar
- Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras, and Ion Androutsopoulos. 2020. LEGAL-BERT: The muppets straight out of law school. arXiv preprint arXiv:2010.02559 (2020).Google Scholar
- PaulF Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017).Google Scholar
- HyungWon Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022).Google Scholar
- Leo Gao, John Schulman, and Jacob Hilton. 2023. Scaling laws for reward model overoptimization. In International Conference on Machine Learning. PMLR, 10835–10866.Google Scholar
- Demi Guo, AlexanderM Rush, and Yoon Kim. 2020. Parameter-efficient transfer learning with diff pruning. arXiv preprint arXiv:2012.07463 (2020).Google Scholar
- Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin DeLaroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790–2799.Google Scholar
- EdwardJ Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021).Google Scholar
- Sagar Joshi, Sumanth Balaji, Aparna Garimella, and Vasudeva Varma. 2022. Graph-based Keyword Planning for Legal Clause Generation from Topics. In Proceedings of the Natural Legal Language Processing Workshop 2022. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Hybrid), 276–286. https://aclanthology.org/2022.nllp-1.26Google Scholar
Cross Ref
- Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, RonanLe Bras, and Yejin Choi. 2022. Maieutic prompting: Logically consistent reasoning with recursive explanations. arXiv preprint arXiv:2205.11822 (2022).Google Scholar
- NitishShirish Keskar, Bryan McCann, LavR Varshney, Caiming Xiong, and Richard Socher. 2019. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858 (2019).Google Scholar
- Nikita Kitaev, Steven Cao, and Dan Klein. 2018. Multilingual constituency parsing with self-attention and pre-training. arXiv preprint arXiv:1812.11760 (2018).Google Scholar
- Nikita Kitaev and Dan Klein. 2018. Constituency parsing with a self-attentive encoder. arXiv preprint arXiv:1805.01052 (2018).Google Scholar
- Takeshi Kojima, ShixiangShane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022), 22199–22213.Google Scholar
- Spyretta Leivaditi, Julien Rossi, and Evangelos Kanoulas. 2020. A benchmark for lease contract review. arXiv preprint arXiv:2010.10386 (2020).Google Scholar
- Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459–9474.Google Scholar
- XiangLisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021).Google Scholar
- Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74–81. https://aclanthology.org/W04-1013Google Scholar
- Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, RonanLe Bras, Yejin Choi, and Hannaneh Hajishirzi. 2021. Generated knowledge prompting for commonsense reasoning. arXiv preprint arXiv:2110.08387 (2021).Google Scholar
- Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2021. GPT understands, too. arXiv preprint arXiv:2103.10385 (2021).Google Scholar
- Jieyi Long. 2023. Large Language Model Guided Tree-of-Thought. arXiv preprint arXiv:2305.08291 (2023).Google Scholar
- Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, BodhisattwaPrasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-Refine: Iterative Refinement with Self-Feedback. arXiv:arXiv:2303.17651Google Scholar
- Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2021. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943 (2021).Google Scholar
- Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2021. Cross-task generalization via natural language crowdsourcing instructions. arXiv preprint arXiv:2104.08773 (2021).Google Scholar
- OpenAI. 2023. GPT-4 Technical Report. arXiv:arXiv:2303.08774Google Scholar
- Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730–27744.Google Scholar
- Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311–318. https://doi.org/10.3115/1073083.1073135Google Scholar
Digital Library
- Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, and Jianfeng Gao. 2023. Instruction tuning with gpt-4. arXiv preprint arXiv:2304.03277 (2023).Google Scholar
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.Google Scholar
- Victor Sanh, Albert Webson, Colin Raffel, StephenH Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, TevenLe Scao, Arun Raja, 2021. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207 (2021).Google Scholar
- John Schulman, Barret Zoph, Christina Kim, Jacob Hilton, Jacob Menick, Jiayi Weng, Juan FelipeCeron Uribe, Liam Fedus, Luke Metz, Michael Pokorny, 2022. ChatGPT: Optimizing language models for dialogue. OpenAI blog (2022).Google Scholar
- Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and PaulF Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems 33 (2020), 3008–3021.Google Scholar
- Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and TatsunoriB Hashimoto. 2023. Stanford alpaca: An instruction-following llama model.Google Scholar
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, AidanN Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).Google Scholar
- Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, NoahA Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560 (2022).Google Scholar
- Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, ArutSelvan Dhanasekaran, Atharva Naik, David Stap, 2022. Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks. arXiv preprint arXiv:2204.07705 (2022).Google Scholar
- Jason Wei, Maarten Bosma, VincentY Zhao, Kelvin Guu, AdamsWei Yu, Brian Lester, Nan Du, AndrewM Dai, and QuocV Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021).Google Scholar
- Tongshuang Wu, Ellen Jiang, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, and CarrieJ Cai. 2022. Promptchainer: Chaining large language model prompts through visual programming. In CHI Conference on Human Factors in Computing Systems Extended Abstracts. 1–10.Google Scholar
Digital Library
- Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, ThomasL Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023).Google Scholar
- EladBen Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021).Google Scholar
- Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, and Maosong Sun. 2020. How does NLP benefit legal system: A summary of legal artificial intelligence. arXiv preprint arXiv:2004.12158 (2020).Google Scholar
- Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Chi. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625 (2022).Google Scholar
Cited By
View all
Index Terms
Adapting Open-Source LLMs for Contract Drafting and Analyzing Multi-Role vs. Single-Role Behavior of ChatGPT for Synthetic Data Generation
Computing methodologies
Artificial intelligence
Natural language processing
Natural language generation
Recommendations
Read More
- Improving theReadability ofGenerated Tests Using GPT-4 andChatGPT Code Interpreter
Search-Based Software Engineering
Abstract
A major challenge in automated test generation is the readability of generated tests. Emerging large language models (LLMs) excel at language analysis and transformation tasks. We propose that improving test readability is such a task and explore ...
Read More
- Instructor Perceptions of AI Code Generation Tools - A Multi-Institutional Interview Study
SIGCSE 2024: Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1
Much of the recent work investigating large language models and AI Code Generation tools in computing education has focused on assessing their capabilities for solving typical programming problems and for generating resources such as code explanations ...
Read More
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in
Full Access
Get this Publication
- Information
- Contributors
Published in
AIMLSystems '23: Proceedings of the Third International Conference on AI-ML Systems
October 2023
381 pages
ISBN:9798400716492
DOI:10.1145/3639856
Copyright © 2023 ACM
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [emailprotected].
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
- Published: 17 May 2024
Permissions
Request permissions about this article.
Author Tags
- Automated Evaluation
- Generative AI
- Large Language Models
- Natural Language Generation
Qualifiers
- research-article
- Research
- Refereed limited
Conference
Funding Sources
Other Metrics
View Article Metrics
- Bibliometrics
- Citations0
Article Metrics
- View Citations
Total Citations
Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
View Author Metrics
Cited By
This publication has not been cited yet
PDF Format
View or Download as a PDF file.
eReader
View online with eReader.
eReader
Digital Edition
View this article in digital edition.
View Digital Edition
HTML Format
View this article in HTML Format .
View HTML Format
- Figures
- Other
Close Figure Viewer
Browse AllReturn
Caption
View Table of Contents
Export Citations
Your Search Results Download Request
We are preparing your search results for download ...
We will inform you here when the file is ready.
Download now!
Your Search Results Download Request
Your file of search results citations is now ready.
Download now!
Your Search Results Download Request
Your search export query has expired. Please try again.