Code-as-Auditor：通过法规到代码的可执行合规推理
Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code
查看机构详情
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出Code-as-Auditor框架，将法规转化为可执行代码和检查清单，通过动态问题引导和自验证循环，实现基于证据的自动化合规评估，在隐私场景中提升准确性和可追溯性。
中文摘要 AI 辅助
大型语言模型（LLMs）越来越多地被用于合规和法律推理任务，然而其输出往往缺乏对法律逻辑和证据的明确依据。我们提出了Code-as-Auditor，一个基于LLM的框架，将模型的推理能力扩展到结构化和有证据依据的合规评估。该框架将法规信息转化为（1）形式化的检查清单和可执行的决策树，将法规和条件编码为可解释的代码结构。在推理过程中，每个检查清单项被（2）动态扩展为事实性和反事实性问题，引导模型基于具体案例的证据和潜在违规进行推理。这一过程建立了一个从证据识别、经规则应用到最终决策的推理管道，同时一个自我验证循环提高了生成代码的逻辑一致性和结果的可追溯性。在隐私和数据保护场景上的实验表明，Code-as-Auditor提供了更准确和有证据支持的评价，使得基于明确监管标准的自动化合规检查成为可能。
英文摘要
Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidence. We present Code-as-Auditor, an LLM-based framework that extends the model's reasoning capability toward structured and evidence-grounded compliance assessment. The framework translates regulatory information into (1) formalized checklists and executable decision trees, encoding regulations and conditions as interpretable code structures. During inference, each checklist item is (2) dynamically expanded into factual and counterfactual questions, guiding the model to reason over case-specific evidence and potential violations. This process establishes a reasoning pipeline that proceeds from evidence identification, through rule application, to final decision-making, while a self-verification loop improves the logical consistency of the generated code and the traceability of outcomes. Experiments on privacy and data protection scenarios demonstrate that Code-as-Auditor delivers more accurate and evidence-backed evaluations, enabling automated compliance regulation checking grounded in explicit regulatory criteria.
