Unverified60% confidenceFactExact time
Sycophancy bias refers to the tendency of a model to cater to users' views even when the user's judgment is wrong, originating from annotators' implicit preference for pleasing answers in RLHF training.
2
Sources
60%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
VerifiedModels trained with RLHF tend to disproportionately change their positions to accommodate users when users explicitly disagree, even when the original answer was correct—this is known as sycophancy bias.80% similarUnverifiedSycophancy 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.80% similarUnverifiedSmall-parameter models (such as those at the 1B scale) are prone to sycophancy, tending to give users positive responses rather than critical evaluations, partly because RLHF training reinforces behavior patterns that "keep users satisfied".76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/530716API
curl https://kongchang.com/api/v1/knowledge/claims/530716MCP
get_claim(id=530716)