Unverified50% confidenceFactExact time
A study published on OpenReview argues that the reasoning tokens generated by LLMs are fundamentally unrelated to human reasoning.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedResearch has found that the chain-of-thought reasoning generated by models does not fully correspond to their actual internal computation processes, and may provide post-hoc explanations unrelated to the true decision-making path.67% similarUnverified思维链提示有效的原理是：LLM是逐词生成的自回归模型，先生成推理过程可作为后续推断的工作记忆，降低直接跳结论的错误率66% similarVerifiedThe root cause of LLM hallucination lies in the autoregressive generation mechanism—the model predicts the next Token based on a probability distribution rather than genuine logical reasoning.66% similarUnverifiedThe root cause of citation hallucination is that LLMs learn linguistic patterns by predicting the next word, and no factual database for real-time verification is embedded in the training process.63% similarUnverified文生图模型的理解本质上是大规模的统计关联而非真正的推理理解63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/828103API
curl https://kongchang.com/api/v1/knowledge/claims/828103MCP
get_claim(id=828103)