chain-of-thought-prompting-technique

IN premiseentries/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: