Unverified50% confidenceConceptExact time
Sycophancy is a widely documented phenomenon in large language model alignment research, referring to a model's tendency to cater to the user's views, stance, or tone rather than adhering to facts or its own judgment.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified奉承偏见（Sycophancy）指模型倾向于迎合用户观点，即便用户判断有误，源于RLHF训练中标注者对令人愉快回答的隐性偏好80% similarUnverifiedAnthropic refers to the phenomenon of a model filtering or distorting contradictory information in order to maintain a preset worldview as 'motivated reasoning.'65% similarVerified大模型幻觉是指语言模型生成看似合理但实际不正确或不存在的内容64% similarUnverifiedSubliminal learning refers to the ability of a language model to covertly convey a hidden feature through outputs that appear unrelated to the target.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019905API
curl https://kongchang.com/api/v1/knowledge/claims/1019905MCP
get_claim(id=1019905)