Explainability

Studying internal mechanisms or input influence on outputs (e.g., saliency maps, SHAP, attention analysis).

Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.

Local surrogate explanation method approximating model behavior near a specific input.

Framework for reasoning about cause-effect relationships beyond correlation, often using structural assumptions and e...

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Automated detection/prevention of disallowed outputs (toxicity, self-harm, illegal instruction, etc.).

Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.