ARGUS：面向美国就业歧视投诉的角色感知事件知识图谱
ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
浏览论文内容
中文总结 AI 辅助
针对美国就业歧视投诉，提出ARGUS流水线，结合5W1H模式和法律模型构建文档级事件知识图谱，实验表明图结构分类优于基线，且EKG检索提升文档级问答。
中文摘要 AI 辅助
美国就业歧视投诉描述了复杂的事件序列，这些序列无法仅通过词汇或基于嵌入的表示来明确捕获。我们提出了ARGUS，一个基于来源的流水线，它结合了受5W1H启发的模式、法律领域模型和基于LLM的结构化生成，从CourtListener投诉中构建文档级事件知识图谱（EKGs）。ARGUS提取包含事实的陈述，构建具有参与者、时间和因果结构的块级事件图，并将它们合并为文档级表示。我们通过人工和多模型评估来评估图谱质量，并在投诉分类和法律问答上测试下游实用性。图结构分类器在保留集上优于原始和线性化基线，仅使用EKG的检索改善了文档范围的问答，而开放检索的收益仍然受到第一阶段候选召回率低的限制。这些结果表明，一旦相关材料被检索到，EKGs在组织和推理证据方面最为有用。
英文摘要
U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or embedding-based representations alone. We present ARGUS, a source-grounded pipeline that combines a 5W1H-inspired schema, legal-domain models, and LLM-based structured generation to construct document-level Event Knowledge Graphs (EKGs) from CourtListener complaints. ARGUS extracts fact-bearing statements, builds chunk-level event graphs with participant, temporal, and causal structure, and merges them into document-level representations. We evaluate graph quality through human and multi-model assessment and test downstream utility on claim classification and legal QA. The graph-structured classifier outperforms raw and linearized baselines on the held-out set, and EKG-only retrieval improves document-scoped QA, while open-retrieval gains remain limited by low first-stage candidate recall. These results suggest that EKGs are most useful for organizing and reasoning over evidence once relevant material has been retrieved.
发表机构
- University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
- Bloomberg（彭博）
机构由 AI 辅助整理，请以论文原文为准。
