新闻
ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- ARGUS builds event knowledge graphs from employment-discrimination complaints using LLMs and legal-domain models to extract structured facts and relationships.
- 为何重要
- Matters for legal tech engineers building document analysis systems, especially those processing complex multi-event narratives in regulated domains.
- 注意
- Graph-structured approach works best for organizing retrieved evidence, not for initial document retrieval; open-retrieval performance remains limited by low recall.
- llm
- embedding
- edge
- eval
这条新闻背后的模式
- Structure-Aware Codebase Retrieval (Repo Map)
- Temporal Knowledge Graph Memory
- Knowledge Graph Construction
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。