[KongchangAI]
Expired50% confidenceFactTime unknown

RLHF is intended to align the model with human preferences, but human preferences tend to reward 'confident and detailed' responses, creating a paradox that reinforces hallucination

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)

Sources

AI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It
bilibili老傅1024

Related Claims

UnverifiedRLHF本质上是优化模型表达风格使其符合人类偏好，而非赋予模型真实情感体验76% 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 completion72% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/54997
API
curl https://kongchang.com/api/v1/knowledge/claims/54997
MCP
get_claim(id=54997)