LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation
This addresses the problem of assessing RAG effectiveness in the legal domain for researchers and practitioners, but it is incremental as it adapts existing RAG concepts to a new domain.
The authors tackled the lack of a benchmark for evaluating retrieval-augmented generation (RAG) systems in legal consultations by proposing LexRAG, which includes 1,013 multi-turn dialogue samples and 17,228 legal articles, and they revealed key limitations of existing RAG systems through experimental analysis.
Retrieval-augmented generation (RAG) has proven highly effective in improving large language models (LLMs) across various domains. However, there is no benchmark specifically designed to assess the effectiveness of RAG in the legal domain, which restricts progress in this area. To fill this gap, we propose LexRAG, the first benchmark to evaluate RAG systems for multi-turn legal consultations. LexRAG consists of 1,013 multi-turn dialogue samples and 17,228 candidate legal articles. Each sample is annotated by legal experts and consists of five rounds of progressive questioning. LexRAG includes two key tasks: (1) Conversational knowledge retrieval, requiring accurate retrieval of relevant legal articles based on multi-turn context. (2) Response generation, focusing on producing legally sound answers. To ensure reliable reproducibility, we develop LexiT, a legal RAG toolkit that provides a comprehensive implementation of RAG system components tailored for the legal domain. Additionally, we introduce an LLM-as-a-judge evaluation pipeline to enable detailed and effective assessment. Through experimental analysis of various LLMs and retrieval methods, we reveal the key limitations of existing RAG systems in handling legal consultation conversations. LexRAG establishes a new benchmark for the practical application of RAG systems in the legal domain, with its code and data available at https://github.com/CSHaitao/LexRAG.