用混合模型解析救灾政策中的隐性矛盾，让专家能看清权力与参与的博弈。
Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance
- 先用大模型识别政策中讨论与管理两类立场，再按规则生成四类逻辑关系。
- 在美英加澳四国100份灾防文件上验证，分析结果准确且跨地区稳定。
- 适合政策研究者、治理学者，可揭示文本中未明说的权力张力。
政策文件塑造治理结果，但其内在逻辑常隐而不显。参与式承诺与管理控制常共存于同一文本，二者间的张力往往未被直接表达。现有计算方法难以捕捉这种由框架驱动的关系，即一个论点并非否定另一个，而是弱化或工具化它。大语言模型端到端摘要虽流畅，却缺乏领域专家可检验或争议的结构。我们提出Apaf，一种将批判性话语分析量化的混合型大模型-符号系统。首先将论点分类为审议型或管理型框架；随后基于大模型提取特征，通过确定性规则生成四种框架中介关系子类型：主体削弱、议程转移、工具支持与规范支持。我们发布了一个包含100个美国、英国、加拿大和澳大利亚灾风险减缓政策子文档的新数据集，并证明生成的论证图在准确性、可解释性和跨司法管辖区稳定性方面表现良好。
原文摘要 · Abstract (English)
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.
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。