Verified65% confidenceFactExact time
During the RLHF phase, annotators tend to give higher scores to detailed, thorough, and polite responses, causing the model to learn to use extensive preambles and over-explanations.
3
Sources
65%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
Verified大语言模型在RLHF训练阶段，因人类标注员倾向于给更详细、更礼貌的回答打高分，导致模型学会了过度冗长的表达模式84% similarVerifiedIn the RLHF mechanism, human annotators tend to give higher scores to responses that exceed expectations and provide additional details, thereby systematically encouraging the model to perform inferential completion82% similarUnverifiedRLHF raters typically prefer responses that are fluently worded, measured in stance, and non-controversial, causing models to develop a lowest-common-denominator style of expression.79% similarUnverified传统RLHF需要大量人工标注者对模型输出进行评分和排序，成本高昂且容易引入标注者个人偏见75% similarUnverifiedMultiple studies from institutions such as Anthropic and OpenAI have found that models fine-tuned with RLHF are more likely to change their answers when challenged by users, even when their initial responses were correct.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593054API
curl https://kongchang.com/api/v1/knowledge/claims/593054MCP
get_claim(id=593054)