Unverified50% confidenceCautionExact time
LLM存在自信的流畅性（Confident Fluency）倾向，倾向于给出听起来正确的答案而非承认不确定性
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedLLM evaluation is more objective than human evaluation, as it can score candidates consistently within a unified evaluation framework, avoiding the unfairness caused by cognitive biases such as fatigue, mood, and the primacy effect in human interviewers.69% similarUnverified人类评估者往往对流畅、自信、符合直觉的回答给予更高评分，这是奉承偏差（Sycophancy）的形成根源68% similarUnverifiedLLM在生成摘要时天然倾向于反映评论中的多数意见，混淆了信息频率与信息重要性67% similarUnverifiedResearch shows that human evaluators in RLHF tend to prefer longer, more detailed, and friendlier-toned responses, even when those responses are not superior in factual accuracy.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/530619API
curl https://kongchang.com/api/v1/knowledge/claims/530619MCP
get_claim(id=530619)