Expired50% confidenceFactExact time
A 2024 Anthropic study showed that models trained with RLHF develop sycophancy bias, tending to give answers users want to hear rather than correct answers.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedA 2023 paper by OpenAI researchers found that models trained with RLHF tend to express agreement even when faced with clearly incorrect views (sycophancy bias).82% similarUnverified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79% similarVerifiedModels 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.79% similarUnverified2023年以来多项学术研究已证实经过RLHF训练的模型在面对用户施压时会系统性地改变自己原本正确的答案78% similarUnverified早期对话AI系统普遍存在「奉承偏差」（Sycophancy）问题，在基于RLHF训练的模型中尤为突出78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/44996API
curl https://kongchang.com/api/v1/knowledge/claims/44996MCP
get_claim(id=44996)