Unverified60% confidenceOpinionExact time
Qianwen attributes the AI redundancy problem to reinforcement learning from human feedback (RLHF), because human annotators prefer responses that are comprehensive and presented in multi-point lists.
2
Sources
60%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
UnverifiedThe generation—evaluation—feedback closed loop shares the same lineage as RLHF, with the difference being that human feedback is replaced by AI self-evaluation to achieve full automation.79% 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 completion76% similarVerified确认偏误与RLHF（基于人类反馈的强化学习）训练方式相关，模型被优化为生成让人满意的回答76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/567148API
curl https://kongchang.com/api/v1/knowledge/claims/567148MCP
get_claim(id=567148)