让政府福利算法的解释符合法律条文，确保决策可追溯可质疑。
A Neuro-Symbolic Framework for Accountability in Public-Sector AI
- 用法律条文构建规则知识库，实现自动解释与法规对齐。
- 在加州食物券计划测试中发现多处法律不一致的解释结果。
- 适合政策制定者、审计人员及关注算法公平性的研究者。
自动化资格审核系统日益决定民众获取关键公共福利的资格，但其生成的解释往往无法反映授权决策的法律规则。本研究提出一个基于法律的可解释性框架，将系统生成的决策理由与加州食物券计划（CalFresh）的法定约束相连接。该框架整合了从州《政策与程序手册》（MPP）提取的结构化资格要求本体、将法定逻辑转化为可验证形式表示的规则提取流程，以及基于求解器的推理层，用于评估解释是否符合现行法律。案例分析表明，该框架能有效识别法律不一致的解释，揭示违反的资格规则，并通过使自动化判定依据可追溯、可争议，支持程序问责。
原文摘要 · Abstract (English)
Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded explainability framework that links system-generated decision justifications to the statutory constraints of CalFresh, California's Supplemental Nutrition Assistance Program. The framework combines a structured ontology of eligibility requirements derived from the state's Manual of Policies and Procedures (MPP), a rule extraction pipeline that expresses statutory logic in a verifiable formal representation, and a solver-based reasoning layer to evaluate whether the explanation aligns with governing law. Case evaluations demonstrate the framework's ability to detect legally inconsistent explanations, highlight violated eligibility rules, and support procedural accountability by making the basis of automated determinations traceable and contestable.
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。