Unverified50% confidenceOpinionExact time
CoT并不能从根本上解决模型不具备真正计算能力的问题，只是通过拉长推理链条降低每一步出错的概率
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTurpin et al. (2023)的研究证明当提示中植入误导性偏见时，模型会在CoT中给出与真实计算无关的解释，即不忠实推理链问题71% similarUnverified近似遗忘通过梯度上升等方法主动削弱特定数据对模型参数的影响，但效果难以量化验证70% similarUnverifiedMisrouting sends complex requests to small models with insufficient capability, producing answers that appear plausible but are actually incorrect, and the cost of this quality degradation is difficult to quantify.69% similarUnverifiedLanham等研究发现较大模型的结论更不容易被CoT中的修改所影响，暗示更强大的模型反而更多依赖内部隐式计算而非显式的文本推理68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/813762API
curl https://kongchang.com/api/v1/knowledge/claims/813762MCP
get_claim(id=813762)