Results for "data → model"

Architecture that retrieves relevant documents (e.g., from a vector DB) and conditions generation on them to reduce hallucinations.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Exponential of average negative log-likelihood; lower means better predictive fit, not necessarily better utility.

System design where humans validate or guide model outputs, especially for high-stakes decisions.

Allows model to attend to information from different subspaces simultaneously.

Logged record of model inputs, outputs, and decisions.

Models trained to decide when to call tools.

Controls amount of noise added at each diffusion step.

Increasing model capacity via compute.

Prompt augmented with retrieved documents.

Risk of incorrect financial models.

Configuration choices not learned directly (or not typically learned) that govern training or architecture.

Attention where queries/keys/values come from the same sequence, enabling token-to-token interactions.

Crafting prompts to elicit desired behavior, often using role, structure, constraints, and examples.

Constraining model outputs into a schema used to call external APIs/tools safely and deterministically.

A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samples.

Encodes token position explicitly, often via sinusoids.

Models time evolution via hidden states.

Using limited human feedback to guide large models.

Maximum system processing rate.

Requirement to provide explanations.

Predicting disease progression or survival.

Acting to minimize surprise or free energy.

Fabrication of cases or statutes by LLMs.

Quantifying financial risk.

A measure of a model class’s expressive capacity based on its ability to shatter datasets.

Measures a model’s ability to fit random noise; used to bound generalization error.

Policies and practices for approving, monitoring, auditing, and documenting models in production.

Framework for identifying, measuring, and mitigating model risks.

Assigning a role or identity to the model.