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
Related terms
Hallucination
When a model confidently makes up something that isn't true.
LLM Evaluation
Measuring whether an LLM does what you want, beyond "looks fine to me".
Perplexity
Exp(average cross-entropy) on held-out text; lower means the model is less surprised by real data.
Reasoning Model
An LLM trained to reason at length internally before answering. Slower and more expensive, but much better on hard problems.
Guardrails
Pre- and post-processing layers that block bad inputs/outputs and enforce policy on top of an LLM.
MMLU (Massive Multitask Language Understanding)
Multiple-choice benchmark across 57 academic subjects; the standard "raw knowledge" headline number.