A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction
This work addresses the competency of LLMs in real-world legal tasks for legal AI applications, but it is incremental as it focuses on evaluation and baseline solutions rather than novel methods.
The paper systematically evaluates large language models (LLMs) on legal judgment prediction, finding that including similar cases and multi-choice options in prompts helps LLMs recall domain knowledge, but an information retrieval (IR) system can sometimes outperform LLM+IR combinations due to limited gains from weaker LLMs.
Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4's law evaluation raise questions concerning their performance in real-world legal tasks. To systematically investigate their competency in the law, we design practical baseline solutions based on LLMs and test on the task of legal judgment prediction. In our solutions, LLMs can work alone to answer open questions or coordinate with an information retrieval (IR) system to learn from similar cases or solve simplified multi-choice questions. We show that similar cases and multi-choice options, namely label candidates, included in prompts can help LLMs recall domain knowledge that is critical for expertise legal reasoning. We additionally present an intriguing paradox wherein an IR system surpasses the performance of LLM+IR due to limited gains acquired by weaker LLMs from powerful IR systems. In such cases, the role of LLMs becomes redundant. Our evaluation pipeline can be easily extended into other tasks to facilitate evaluations in other domains. Code is available at https://github.com/srhthu/LM-CompEval-Legal