用大模型让法律检索从找相似事实转为找核心法律问题。
Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries
- 通过生成法律问题引导检索，精准匹配案件核心争议点。
- 在FIRE数据集上实现MAP 0.36、MAR 0.67，远超基准0.1573。
- 自动生成解释并结构化摘要，适合法律研究与司法辅助场景。
识别相关判例仍具挑战，因多数检索方法侧重事实相似性而非法律问题，且现有系统常缺乏阐明案件相关性的解释。本文提出利用大语言模型（LLM）自主完成案例检索、生成相关性解释及识别核心法律问题，无需法律专业知识。方法结合检索增强生成（RAG）与专为印度判例优化的结构化摘要，基于增广问题引导检索（AQgR）框架，根据事实情境生成针对性法律问题，更高效定位相关判例。结构化摘要由法律专家人工评估，因无合适结构化摘要数据集。判例检索在FIRE数据集上评估，解释由法律专家审核，因解释生成与检索同步属新兴方向。在FIRE 2019子集上的实验显示，平均精度（MAP）达0.36，平均召回率（MAR）达0.67，显著优于当前0.1573的基准。该工作引入多项创新，推动判例检索发展。从以事实为基础转向以法律问题为基础的检索，使结果更契合法律专业人士需求；通过在检索中融入法律问题，提升查询上下文的精确性与意义。
原文摘要 · Abstract (English)
Identifying relevant legal precedents remains challenging, as most retrieval methods emphasize factual similarity over legal issues, and current systems often lack explanations clarifying case relevance. This paper proposes the use of Large Language Models (LLMs) to address this gap by facilitating the retrieval of relevant cases, generating explanations to elucidate relevance, and identifying core legal issues all autonomously, without requiring legal expertise. Our approach combines Retrieval Augmented Generation (RAG) with structured summaries optimized for Indian case law. Leveraging the Augmented Question-guided Retrieval (AQgR) framework, the system generates targeted legal questions based on factual scenarios to identify relevant case law more effectively. The structured summaries were assessed manually by legal experts, given the absence of a suitable structured summary dataset. Case law retrieval was evaluated using the FIRE dataset, and explanations were reviewed by legal experts, as explanation generation alongside case retrieval is an emerging innovation. Experimental evaluation on a subset of the FIRE 2019 dataset yielded promising outcomes, achieving a Mean Average Precision (MAP) score of 0.36 and a Mean Average Recall (MAR) of 0.67 across test queries, significantly surpassing the current MAP benchmark of 0.1573. This work introduces a suite of novel contributions to advance case law retrieval. By transitioning from fact-based to legal-issue-based retrieval, the proposed approach delivers more contextually relevant results that align closely with legal professionals' needs. Integrating legal questions within the retrieval process through the AQgR framework ensures more precise and meaningful retrieval by refining the context of queries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。