1
It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
不只是谄媚：新研究揭示LLM的顺从行为源于认知不确定性，为理解模型输出偏差提供新视角。
arXiv:2605.27288v1 Announce Type: cross Abstract: Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. …