Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Source
Jason Wei et al.
Author
Jason Wei et al.
Published
Why it matters
The finding that asking for the working, not just the answer, changes what a model can solve — and that the effect only emerges above a certain scale. It is the ancestor of every reasoning mode, and why 'think step by step' became infrastructure rather than a trick.
articleWhen Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM ReasoningTughanbulut Kurtulush
articleReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao et al.