实体
MedHallu
MedHallu
PulseAugur coverage of MedHallu — every cluster mentioning MedHallu across labs, papers, and developer communities, ranked by signal.
总计 · 30天
2
90 天内 2
发布 · 30天
0
90 天内 0
论文 · 30天
2
90 天内 2
层级分布 · 90 天
最近 · 第 1/1 页 · 共 2 条
-
New research reveals limits of spectral diagnostics in understanding LLM hallucinations
Researchers have developed a new diagnostic framework to understand how large language models hallucinate by analyzing their self-attention mechanisms. The proposed method, which focuses on the "transport" properties of…
-
CareGuardAI框架提升了患者端医疗保健LLM的安全性和准确性
研究人员开发了CareGuardAI，一个旨在减轻用于患者端医疗保健应用的大型语言模型（LLM）的临床风险和幻觉的新安全框架。该系统借鉴了ISO 14971，纳入了临床安全和事实可靠性的风险评估模块。CareGuardAI采用多阶段管道，包含一个控制器智能体和双重风险评估，以确保响应在发布给患者之前达到安全阈值。