Model Card
Also known as: Model documentation
Structured release doc covering training data, evals, limitations, and intended use of a model.
A structured document published with a model release describing intended use, training data, evaluation results, known limitations, and ethical considerations. Standardized by Mitchell et al. (2019); used by every major lab.
In practice
Reading model cards critically is a senior-level eval skill. Interviews probe what's typically missing (data details, fine-grained capability evals).
Related topics
Questions that mention this term
Related terms
Chatbot Arena
Crowdsourced blind A/B comparisons of LLM responses, aggregated into an Elo leaderboard.
Eval Harness
A framework for running, scoring, and tracking LLM evals over time; handles golden sets, judges, and regressions.
Golden Set
Curated test cases with expected outputs; your regression suite for prompt and model changes.
Guardrails
Pre- and post-processing layers that block bad inputs/outputs and enforce policy on top of an LLM.
Hallucination
When a model confidently makes up something that isn't true.
HumanEval
Code-generation benchmark: 164 problems with hidden unit tests, scored by whether the generated code passes.