通过结构化提示实现可解释的规则应用：一种神经-符号方法
Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach
AI总结：
本文提出一种将推理分解为实体识别、属性提取和符号规则应用三步的结构化提示框架，融合神经与符号方法以提升规则应用的一致性和可解释性，并在LegalBench传闻证据判定任务上使OpenAI o系列模型的F1分数显著提升。
摘要：
大型语言模型（LLMs）在复杂推理任务中表现出色，但在一致的规则应用、异常处理和可解释性方面存在困难，尤其是在法律分析等既需要自然语言理解又需要精确逻辑推理的领域。本文引入了一个结构化提示框架，将推理分解为三个可验证的步骤：实体识别、属性提取和符号规则应用。通过整合神经方法与符号方法，我们的方法利用了LLMs的解释灵活性，同时通过形式验证确保逻辑一致性。该框架将任务定义外部化，使领域专家能够在不改变架构的情况下优化逻辑结构。在LegalBench传闻证据判定任务上评估时，我们的方法显著优于基线，OpenAI o系列模型表现出大幅改进——使用带有互补谓词的结构化分解，o1的F1分数达到0.929，o3-mini达到0.867，而它们少样本基线的F1分数分别为0.714和0.74。这种混合神经-符号系统为透明且一致的基于规则的推理提供了一条有前景的路径，表明在结构化法律推理任务中具有可解释人工智能应用的潜力。
英文摘要：
Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language understanding and precise logical inference. This paper introduces a structured prompting framework that decomposes reasoning into three verifiable steps: entity identification, property extraction, and symbolic rule application. By integrating neural and symbolic approaches, our method leverages LLMs' interpretive flexibility while ensuring logical consistency through formal verification. The framework externalizes task definitions, enabling domain experts to refine logical structures without altering the architecture. Evaluated on the LegalBench hearsay determination task, our approach significantly outperformed baselines, with OpenAI o-family models showing substantial improvements - o1 achieving an F1 score of 0.929 and o3-mini reaching 0.867 using structured decomposition with complementary predicates, compared to their few-shot baselines of 0.714 and 0.74 respectively. This hybrid neural-symbolic system offers a promising pathway for transparent and consistent rule-based reasoning, suggesting potential for explainable AI applications in structured legal reasoning tasks.
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。
