chain-of-thought-prompting-technique
IN premise — entries/2026/06/21/wiki-Large_language_model-chunk-5.md
Created 2026-06-21T09:50:09+00:00
Chain-of-thought prompting (Wei et al. 2022) elicits reasoning by having models show intermediate steps — it is a prompting technique, not an architectural change
Summary
Asking a model to write out its step-by-step reasoning before giving a final answer pulls better thinking out of it, without needing to redesign or retrain the model at all. In other words, the capability is already sitting inside the system, and a well-phrased question is enough to unlock it, which makes this a cheap and practical lever for improving performance.
Dependents
These beliefs depend on this one:
- IN structured-reasoning-prompting-evolved-from-linear-to-branching — Prompting for reasoning evolved from linear chain-of-thought (single path) to self-consistency (multiple paths, majority vote) to tree-of-thoughts (branching with backtracking), progressively adding search structure.