ReaKase-8B: Legal Case Retrieval via Knowledge and Reasoning Representations with LLMs

TL;DR

ReaKase-8B introduces a novel legal case retrieval framework that leverages legal facts, issues, relations, and reasoning with fine-tuned large language models to significantly improve retrieval accuracy.

Contribution

The paper presents a new approach integrating legal reasoning and knowledge representations into case embeddings using LLMs, enhancing retrieval performance.

Findings

Substantial performance improvements over baseline models on COLIEE datasets.

Effective incorporation of legal relations and reasoning enhances case differentiation.

Open-source code available for reproducibility.

Abstract

Legal case retrieval (LCR) is a cornerstone of real-world legal decision making, as it enables practitioners to identify precedents for a given query case. Existing approaches mainly rely on traditional lexical models and pretrained language models to encode the texts of legal cases. Yet there are rich information in the relations among different legal entities as well as the crucial reasoning process that uncovers how legal facts and legal issues can lead to judicial decisions. Such relational reasoning process reflects the distinctive characteristics of each case that can distinguish one from another, mirroring the real-world judicial process. Naturally, incorporating such information into the precise case embedding could further enhance the accuracy of case retrieval. In this paper, a novel ReaKase-8B framework is proposed to leverage extracted legal facts, legal issues, legal relation triplets and legal reasoning for effective legal case retrieval. ReaKase-8B designs an in-context legal case representation learning paradigm with a fine-tuned large language model. Extensive experiments on two benchmark datasets from COLIEE 2022 and COLIEE 2023 demonstrate that our knowledge and reasoning augmented embeddings substantially improve retrieval performance over baseline models, highlighting the potential of integrating legal reasoning into legal case retrieval systems. The code has been released on https://github.com/yanran-tang/ReaKase-8B.