发表机构
New Mexico State University; Sun Yat-Sen University（新墨西哥州立大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究灾害治理中政策文件推理隐含问题，提出混合大语言模型-符号框架Apaf，通过分类论点、生成框架介导关系子类型进行关键话语分析，发布新数据集，论证图准确、可解释且跨辖区稳定。
AI 中文摘要
政策文件塑造治理结果，但其推理往往隐含。参与承诺和管理控制常共存于同一文本，其间张力很少直接阐述。现有政策话语计算方法无法表达驱动这些张力的框架介导关系。大语言模型的端到端摘要生成流畅文本，但结构少难以供领域专家检查或质疑。我们提出Apaf，一种混合大语言模型-符号管道，将关键话语分析作为政策文本上的定量双极论证框架。先将论点分类为审议或管理框架，再通过基于大语言模型提取特征的确定性规则生成四种框架介导关系子类型。我们发布了一个包含来自美国、英国、加拿大和澳大利亚的100份减灾政策子文档的新数据集，并表明生成的论证图准确、可解释且在不同司法管辖区稳定。
英文摘要
Policy documents shape governance outcomes, but their reasoning is often implicit. Participatory commitments and managerial control routinely coexist in the same text, and the tensions between them are rarely stated directly. Existing computational approaches to policy discourse cannot express the frame-mediated relations that drive these tensions, where one argument narrows or instrumentalizes another rather than rejecting it. End-to-end summarization by large language models produces fluent text but offers little structure that domain experts can inspect or contest. We present Apaf, a hybrid LLM--symbolic pipeline that operationalizes critical discourse analysis as a quantitative bipolar argumentation framework over policy text. Arguments are first classified into deliberative or managerial frames. Four frame-mediated relation subtypes (agency reduction, agenda shift, instrumental support, and normative support) are then produced by deterministic rules over LLM-extracted features. We release a novel dataset of 100 sub-documents of disaster-risk-reduction policy from the USA, UK, Canada, and Australia, and show that the resulting argument graphs are accurate, interpretable, and stable across jurisdictions.
