Fig.1

Concept

Chain-of-thought

Chain-of-thought (CoT) is a prompting technique where you ask an LLM to produce intermediate reasoning steps before its final answer, rather than emitting the answer directly. The mechanism is simple: the tokens the model generates become part of its own context, so writing…

The rest of “Chain-of-thought” 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

← Back to the library

Chain-of-thought, explained · Fig. 1