Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents

With the growing potential of large language models (LLMs) in the legal domain, domainspecific finetuning and retrieval-augmented generation (RAG) methods have received widespread attention. However, current methods still suffer from hallucination risk and failing to resolve semantic drift and adapt to varying citation numbers. To address this, we propose Authoritative and Accurate Lawyer (AALawyer), a complementary dual-retriever framework based on the Legal Syllogism and the nature of different legal data. First, we introduce Symbolic Constrained Retrieval (SCR) for closed-set article retrieval, by constraining retrieval to the generative prediction. Second, we build Analogical Precedent Retrieval (APR) to retrieve open-set judicial precedents for reasoning with a newly collected large criminal dataset. Extensive experiments, including Law-Bench, our Hallucination Risk-Benchmark, and comprehensive ablation studies, demonstrate the effectiveness of AALawyer, which mitigates hallucinations while improving the explainability of legal reasoning. Code is available here.