Unverified50% confidenceOpinionExact time
CoT提示词并非教模型新技能，而是激活模型在预训练阶段习得的链式推理能力
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Why Does Chain-of-Thought (CoT) Boost Reasoning? A Four-Layer Deep Dive
bilibiliAI-Agent搭建7/7/2026
Related Claims
UnverifiedSelf-supervised learning is the core paradigm of the pre-training phase, where the model constructs training signals from the data itself through a next-token prediction task.73% similarUnverifiedSkill本质上是通过模拟少样本学习效果，在不修改模型权重的前提下，通过提示模板约束模型的输出分布72% similarUnverified如果模型能理解行为准则背后的深层原因，即使面对训练中从未遇到的全新场景也能做出合理的行为选择，实现可泛化的对齐72% similarUnverifiedWhen a Skill is presented in the form of a few-shot example set, it essentially leverages the model's In-Context Learning capability without modifying the model weights.70% similarUnverifiedThe Ziyue large model made extensive use of educational corpora such as textbooks, exercises, and problem-solving processes during the pre-training and fine-tuning stages, giving it stronger professionalism on educational tasks.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/233243API
curl https://kongchang.com/api/v1/knowledge/claims/233243MCP
get_claim(id=233243)