用大模型重写法律检索查询，解决术语不匹配问题。
GuRE:Generative Query REwriter for Legal Passage Retrieval
- 用大模型训练查询重写，生成更匹配法条的检索词。
- 在多个数据集上显著提升检索效果，超越所有基线方法。
- 重写策略比直接微调检索器更适合真实法律场景。
法律段落检索（LPR）系统对律师起草法律意见书具有重要意义，但该领域仍研究不足。主要瓶颈在于查询与目标段落间存在显著词汇差异。为此，本文提出一种简单有效的生成式查询重写方法——GuRE，利用大语言模型（LLM）进行查询重写训练，使重写后的查询能有效缓解词汇错配问题，从而提升检索性能。实验表明，GuRE在无需依赖特定检索器的前提下，显著优于所有基线方法。进一步分析显示，不同训练目标会导致不同的检索行为，使GuRE相比直接微调检索器更适用于实际应用场景。代码已开源：github.com/daehuikim/GuRE。
原文摘要 · Abstract (English)
Legal Passage Retrieval (LPR) systems are crucial as they help practitioners save time when drafting legal arguments. However, it remains an underexplored avenue. One primary reason is the significant vocabulary mismatch between the query and the target passage. To address this, we propose a simple yet effective method, the Generative query REwriter (GuRE). We leverage the generative capabilities of Large Language Models (LLMs) by training the LLM for query rewriting. "Rewritten queries" help retrievers to retrieve target passages by mitigating vocabulary mismatch. Experimental results show that GuRE significantly improves performance in a retriever-agnostic manner, outperforming all baseline methods. Further analysis reveals that different training objectives lead to distinct retrieval behaviors, making GuRE more suitable than direct retriever fine-tuning for real-world applications. Codes are avaiable at github.com/daehuikim/GuRE.
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。