Exploring the Effectiveness of Prompt Engineering for Legal Reasoning Tasks

The use of large language models (LLMs) for zero-or few-shot prompting in natural language processing has given rise to a new research area known as prompt engineering, which shows promising improvement in tasks such as arithmetic and common-sense reasoning. This paper explores the use of such approaches in legal reasoning tasks by conducting experiments on the COLIEE entailment task, which is based on the Japanese Bar exam. We further evaluate zero-shot/few-shot and fine-tuning approaches with and without explanations, alongside various prompting strategies. Our results indicate that while these techniques can improve general performance, the best results are achieved with prompts derived from specific legal reasoning techniques, such as IRAC (Issue, Rule, Application, Conclusion). In addition, we observe that few-shot learning with demonstrations derived from clustering past training data consistently yields high performance on the most recent COLIEE entailment tasks. Through our experiments, we improve the previous best result on the 2021 COLIEE task from 0.7037 to 0.8025 and surpass the best system from 2022 with an accuracy of 0.789.