Chain of thought
Also: chain-of-thought
Having the model write out its steps before the final answer. It often helps, but the written steps are not proof the answer is right.
The fuller definition
Chain of thought refers to intermediate reasoning steps associated with solving a task. Some methods prompt for written steps; some models perform internal reasoning that is not exposed.
Invented probabilities. Always picking the top candidate gives the same wording every run; sampling sometimes picks a lower one. Neither setting checks whether the sentence is true.
A concrete example
A worked calculation shows its inputs and arithmetic so a reader can check the result.
The distinction that matters
A generated explanation need not faithfully describe the model's internal computation. Request inspectable evidence rather than assumed access to private thinking.
Related terms
Reasoning model
A model trained to spend extra work on some answers. It may help with hard tasks. It can still be wrong, and speed and cost vary.
Reliability & securityEvaluation (eval)
Testing an AI tool on a set of tasks to see how well it actually does.
Prompting & contextPrompt
What you give a model to guide its reply. This may include a question, rules, and source text.
Where it is taught
How models learn from examplesSource and further reading
Hugging Face · LLM courseThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.