Enhancing Legal Case Retrieval via Scaling High-quality Asymmetric Query-Candidate Pairs

Anonymous

Abstract: Legal case retrieval (LCR) aims to provide similar cases as references for a given fact description. This task is crucial for promoting consistent judgments in similar cases, effectively enhancing judicial fairness and improving work efficiency for judges. However, existing works face two main challenges for real-world applications: existing works mainly focus on case-to-case retrieval using lengthy queries, which does not match real-world scenarios; and the limited data scale, with current datasets containing only hundreds of queries, is insufficient to satisfy the training requirements of existing data-hungry neural models. To address these issues, we introduce an automated method to construct asymmetrically query-candidate pairs and construct the largest LCR dataset to date, LEAD, which is hundreds of times larger than existing datasets. This dataset can provide ample training signals for LCR models. Experimental results demonstrate that models training with LEAD can achieve state-of-the-art results on two widely used LCR benchmarks. Besides, the construction method can be also applied to civil cases and achieve promising results. The code and dataset used in this paper will be released to promote the development of LCR.

Paper Type: long

Research Area: Information Retrieval and Text Mining

Languages Studied: Chinese