研究人员开发了一个名为LegalHalluLens的新框架，用于审计和缓解法律应用中AI系统的幻觉。该框架识别特定类型的幻觉，如数字、时间或事实错误，并引入风险方向指数（RDI）来量化遗漏信息与捏造信息之间的偏差。通过分析大量法律合同数据集，该系统揭示了不同声明类别之间被聚合指标隐藏的显著性能差距。此外，LegalHalluLens采用了一个经过校准的多主体辩论管道，利用这些诊断见解来提高准确性并减少虚假检测，从而在法律环境中实现更值得信赖的AI部署。
AI
arXiv:2606.18021v1 Announce Type: new Abstract: AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable…
AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present L…
LegalHalluLens audits AI systems in legal workflows by identifying specific error patterns and directional biases in hallucinations across different claim types, enabling more reliable deployment through targeted diagnostic and mitigation approaches.
arXiv cs.LG
TIER_1English(EN)·Muhammad Osama, Maheera Amjad, Zartasha Mustansar, Arslan Shaukat, Muhammad U. S. Khan·
arXiv:2606.14149v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdraw…
arXiv cs.LG
TIER_1English(EN)·Muhammad U. S. Khan·
Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdrawn pharmaceuticals when answering clinical questi…
<p>AI hallucinations rarely look broken at first glance. They look confident, polished, and ready to ship.</p> <p>That is the dangerous part.</p> <p>A generated report can cite a customer that never said yes. A support answer can invent a policy. A data assistant can explain a me…
