Results for "data → model"

Credit models with interpretable logic.

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Maximum number of tokens the model can attend to in one forward pass; constrains long-document reasoning.

A model that assigns probabilities to sequences of tokens; often trained by next-token prediction.

Constraining outputs to retrieved or provided sources, often with citation, to improve factual reliability.

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

The shape of the loss function over parameter space.

Extracting system prompts or hidden instructions.

Optimizes future actions using a model of dynamics.

Mathematical representation of friction forces.

Internal representation of the agent itself.

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.

Fraction of correct predictions; can be misleading on imbalanced datasets.

Often more informative than ROC on imbalanced datasets; focuses on positive class performance.

Generates sequences one token at a time, conditioning on past tokens.

Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.

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

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Routes inputs to subsets of parameters for scalable capacity.

Joint vision-language model aligning images and text.

Formal model linking causal mechanisms and variables.

Incrementally deploying new models to reduce risk.

Learned subsystem that optimizes its own objective.

Breaking tasks into sub-steps.

Temporary reasoning space (often hidden).

Small prompt changes cause large output changes.

Probabilities do not reflect true correctness.

Restricting distribution of powerful models.

A table summarizing classification outcomes, foundational for metrics like precision, recall, specificity.

Harmonic mean of precision and recall; useful when balancing false positives/negatives matters.