作者位次 #3/6ACL 2026Poster· Natural Language Processing
Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents
Zixuan Huang · Yanxiang Ma · Luhan Wang · Yunke Wang · Duo Shi · Chang Xu
摘要
With the growing potential of large language models (LLMs) in the legal domain, domain-specific 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 a...