Verified65% confidenceFactTime unknown
The training objective of current large language models is to generate responses that satisfy the user, not to generate correct responses.
3
Sources
65%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified早期经RLHF训练的大型语言模型倾向于给出用户喜欢的回答，产生迎合性偏差（sycophancy）77% similarVerifiedAfter reinforcement learning from human feedback (RLHF), mainstream large language models naturally tend to produce satisfying and easily accepted responses rather than actively raising criticisms76% similarUnverifiedA large language model is essentially a one-question-one-answer system that takes a Prompt as input and outputs an Answer75% similarUnverifiedAnswer engines adopt a "retrieve-understand-generate" paradigm: first retrieving relevant documents, then using a large language model to understand the content, and finally synthesizing a coherent natural language answer.75% similarUnverifiedLarge language models are trained on massive corpora that may already contain extensive mathematical literature, problem-solving processes, and even answers to similar problems.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5452API
curl https://kongchang.com/api/v1/knowledge/claims/5452MCP
get_claim(id=5452)