用多跳推理让合规检测可解释，自动生成法律论证链条。
Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure
- 将合规论证拆解为多跳自然语言推理任务，实现可追溯判断。
- 利用大模型生成保障案例，解决数据稀缺问题，覆盖率达87.3%。
- 适合需要透明合规验证的监管科技与系统安全领域。
确保复杂系统符合法规通常依赖于通过论点-证据框架验证保障案例的有效性。该过程面临法律与技术文本复杂、模型需提供解释、保障案例数据有限等挑战。本文提出基于自然语言推理（NLI）的可解释合规检测方法：EXplainable CompLiance detection with Argumentative Inference of Multi-hop reasoning（EXCLAIM）。将保障案例的论点-论据-证据结构建模为多跳推理任务，以实现可解释且可追踪的合规判断。针对保障案例数据不足问题，使用大语言模型（LLMs）生成合成案例，并引入覆盖率与结构一致性指标进行评估。以GDPR要求为例的多跳推理实证研究显示，生成案例在任务中表现良好。结果表明，基于NLI的方法在自动化监管合规方面具有潜力。
原文摘要 · Abstract (English)
Ensuring complex systems meet regulations typically requires checking the validity of assurance cases through a claim-argument-evidence framework. Some challenges in this process include the complicated nature of legal and technical texts, the need for model explanations, and limited access to assurance case data. We propose a compliance detection approach based on Natural Language Inference (NLI): EXplainable CompLiance detection with Argumentative Inference of Multi-hop reasoning (EXCLAIM). We formulate the claim-argument-evidence structure of an assurance case as a multi-hop inference for explainable and traceable compliance detection. We address the limited number of assurance cases by generating them using large language models (LLMs). We introduce metrics that measure the coverage and structural consistency. We demonstrate the effectiveness of the generated assurance case from GDPR requirements in a multi-hop inference task as a case study. Our results highlight the potential of NLI-based approaches in automating the regulatory compliance process.
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。