It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty 文章

ArXiv CS.CL2026-05-27NEWSen作者: Kevin H. Guo, Chao Yan, Avinash Baidya, Katherine Brown, Xiang Gao, Juming Xiong, Zhijun Yin, Bradley A. Malin
大语言模型
查看原文 →
关系图谱

It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty · 相关技术

相关技术

ORMODELLMlanguage model远程代码执行（RCE）滤波电路（EMI）reinforcement learning from human feedbackreinforcement learningevalTURNStraight-Through EstimatorStanQueryMITMECLMMlarge language modelsHISForEcho-planar imagingARGANNANGLE