Explainability
Also: explainable AI, XAI, interpretability
Being able to understand why a system gave the answer it did.
The fuller definition
Explainability refers to methods and features that help people understand why a system produced an output. For language models, a generated explanation is itself an output that may not reflect the actual computation.
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 classifier highlights the passages that most influenced a label so a reviewer can check them.
The distinction that matters
A fluent because paragraph is not a mechanism report. Prefer inspectable evidence over narrated reasoning.
Related terms
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.
FoundationsAttention
A way for a model to weigh links between parts of its input. The weights help it process text. They do not show which claims are true.
Reliability & securityEvaluation (eval)
Testing an AI tool on a set of tasks to see how well it actually does.
Where it is taught
Why the same question can produce different answersSource and further reading
Anthropic · Evaluating AI agentsThe 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.