Concept
Chain-of-thought prompting
Chain-of-thought (CoT) prompting is a technique where you steer a large language model to produce intermediate reasoning steps before its final answer, rather than jumping straight to the answer. It works entirely at inference time, with no finetuning and no weight changes.
The rest of “Chain-of-thought prompting” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→