提升法律大语言模型响应：利用可训练逻辑结构和语义知识进行法律推理
Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning
AI总结：
针对法律问答任务中LLMs泛化、幻觉及现有RAG忽略逻辑结构的问题，提出逻辑-语义整合模型（LSIM），通过强化学习生成事实-规则链、DSSM检索及上下文学习生成答案，显著提升了准确性和可靠性。
摘要：
大语言模型（LLMs）在众多领域取得了令人瞩目的成果，但在法律问答任务中存在显著不足。LLMs常生成缺乏专家法律建议所需逻辑特异性的泛化响应，且易产生幻觉，提供看似正确却不可靠的答案。检索增强生成（RAG）技术为这一挑战提供了部分解决方案，但现有方法通常仅关注语义相似性，忽略了法律推理必需的逻辑结构。本文提出逻辑-语义整合模型（LSIM），这是一种连接语义与逻辑连贯性的新型监督框架。LSIM包含三个组件：强化学习为每个问题预测结构化事实-规则链，可训练的深度结构化语义模型（DSSM）通过整合语义和逻辑特征检索最相关的候选问题，上下文学习利用检索内容生成最终答案。我们在真实世界法律问答数据集上的实验（经自动指标和人工评估验证）表明，与现有方法相比，LSIM显著提升了准确性和可靠性。
英文摘要：
Large Language Models (LLMs) have achieved impressive results across numerous domains, yet they experience notable deficiencies in legal question-answering tasks. LLMs often generate generalized responses that lack the logical specificity required for expert legal advice and are prone to hallucination, providing answers that appear correct but are unreliable. Retrieval-Augmented Generation (RAG) techniques offer partial solutions to address this challenge, but existing approaches typically focus only on semantic similarity, neglecting the logical structure essential to legal reasoning. In this paper, we propose the Logical-Semantic Integration Model (LSIM), a novel supervised framework that bridges semantic and logical coherence. LSIM comprises three components: reinforcement learning predicts a structured fact-rule chain for each question, a trainable Deep Structured Semantic Model (DSSM) retrieves the most relevant candidate questions by integrating semantic and logical features, and in-context learning generates the final answer using the retrieved content. Our experiments on a real-world legal QA dataset-validated through both automated metrics and human evaluation-demonstrate that LSIM significantly enhances accuracy and reliability compared to existing methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
