LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
LegalHalluLens: 类型化幻觉审计与校准的多智能体辩论以实现可信赖的法律AI
机构 * Independent Researcher, Sunnyvale, CA, USA(独立研究者,美国加州太阳谷) ; Independent Researcher, San Diego, CA, USA(独立研究者,美国加州圣地亚哥)
专题命中 诊断辅助 :diagnosis(abstract);分类 cs.LG
AI总结 针对法律AI中聚合指标掩盖的错误集中性和方向性问题,提出LegalHalluLens审计框架,通过类型化幻觉画像、风险方向指数(RDI)和校准辩论管道,将幻觉检测减少45%,并揭示聚合指标隐藏的失败模式。
Comments 15 pages, 5 figures; Published at the Second Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD) at ICML 2026