AI RESEARCH
Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval
arXiv CS.CL
•
ArXi:2605.24454v1 Announce Type: new Large language models (LLMs) have shown strong performance in the legal domain, nstrating notable potential in Legal Question Answering (LQA). However, unlike general QA, LQA requires answers that are not only accurate but also rigorously grounded in explicit legal authority. In statutory LQA, many questions require multi-hop reasoning across multiple legal issues, substantially increasing the risk of hallucination, thereby making accurate retrieval of ing statutory provisions a critical prerequisite.