让法律大模型更精准，通过逻辑与语义结合提升回答可靠性。
Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning
- 用强化学习构建法律事实-规则链，增强推理结构
- 在真实法律数据集上准确率显著优于现有方法
- 适合需要高可靠性的法律AI应用开发者
大型语言模型在多个领域表现优异，但在法律问答任务中仍存在明显缺陷：生成答案常缺乏专家级逻辑严谨性，且易产生幻觉。检索增强生成（RAG）虽部分缓解此问题，但多数方法仅依赖语义相似度，忽视法律推理必需的逻辑结构。本文提出逻辑-语义融合模型（LSIM），一个监督式框架，整合语义与逻辑一致性。LSIM包含三部分：强化学习预测每道题的事实-规则链；可训练的深度结构化语义模型（DSSM）联合语义与逻辑特征检索最相关问题；上下文学习基于检索内容生成最终答案。在真实法律问答数据集上的实验表明，经自动化指标与人工评估验证，LSIM在准确率和可靠性上显著优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。