LegalSearchLM：将法律案例检索重构为法律要素生成

LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation

May 28, 2025

作者: Chaeeun Kim, Jinu Lee, Wonseok Hwang

cs.AI

摘要

法律案例检索（Legal Case Retrieval, LCR）是从查询案例中检索相关案例的一项基础任务，对法律专业人士的研究与决策至关重要。然而，现有LCR研究面临两大局限：首先，它们多在规模相对较小的检索语料库（如100至55K案例）上进行评估，且使用的刑事查询类型范围狭窄，难以充分反映现实法律检索场景的复杂性；其次，这些研究依赖基于嵌入或词汇匹配的方法，往往导致表征有限且匹配结果在法律上不相关。为解决这些问题，我们提出：(1) LEGAR BENCH，首个大规模韩语LCR基准，涵盖120万法律案例中的411种多样化犯罪类型查询；(2) LegalSearchLM，一种检索模型，通过对查询案例进行法律要素推理，并通过约束解码直接生成基于目标案例的内容。实验结果表明，LegalSearchLM在LEGAR BENCH上以6-20%的优势超越基线模型，达到最先进性能。此外，该模型在跨域案例上展现出强大的泛化能力，比仅在域内数据上训练的朴素生成模型高出15%。

English

Legal Case Retrieval (LCR), which retrieves relevant cases from a query case, is a fundamental task for legal professionals in research and decision-making. However, existing studies on LCR face two major limitations. First, they are evaluated on relatively small-scale retrieval corpora (e.g., 100-55K cases) and use a narrow range of criminal query types, which cannot sufficiently reflect the complexity of real-world legal retrieval scenarios. Second, their reliance on embedding-based or lexical matching methods often results in limited representations and legally irrelevant matches. To address these issues, we present: (1) LEGAR BENCH, the first large-scale Korean LCR benchmark, covering 411 diverse crime types in queries over 1.2M legal cases; and (2) LegalSearchLM, a retrieval model that performs legal element reasoning over the query case and directly generates content grounded in the target cases through constrained decoding. Experimental results show that LegalSearchLM outperforms baselines by 6-20% on LEGAR BENCH, achieving state-of-the-art performance. It also demonstrates strong generalization to out-of-domain cases, outperforming naive generative models trained on in-domain data by 15%.