Unverified50% confidenceFactExact time
RLHF's optimization for fluency and confident expression may in turn reinforce confident but incorrect statements.
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
UnverifiedRLHF中人类评审倾向给流畅自信全面的答案更高分而较少关注事实核查，导致模型获得隐性激励表现得有把握比实际有把握更重要77% similarUnverifiedRLHF对齐存在'过度对齐'问题，模型在完全无害的场景下也会过度谨慎，频繁拒绝正常的创意写作和角色扮演请求67% similarUnverifiedLarge language models commonly suffer from overconfidence and require prompt engineering and calibration strategies to calibrate confidence levels.65% similarUnverifiedRLHF relies on human evaluators to judge the quality of AI outputs, and this method will fail when AI capabilities surpass the range of human comprehension.63% similarUnverifiedRLHF存在奖励黑客行为等根本性局限，当AI能力超越评估员水平时人类评估的可靠性也会下降63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/600442API
curl https://kongchang.com/api/v1/knowledge/claims/600442MCP
get_claim(id=600442)