Adapting Open-Source LLMs for Contract Drafting and Analyzing Multi-Role vs. Single-Role Behavior of ChatGPT for Synthetic Data Generation
Jaykumar Kasundra, Shreyans Dhankhar · 2023
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.