Results for "causal generation"

Rules and controls around generation (filters, validators, structured outputs) to reduce unsafe or invalid behavior.

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

Scales logits before sampling; higher increases randomness/diversity, lower increases determinism.

Samples from the k highest-probability tokens to limit unlikely outputs.

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Stress-testing models for failures, vulnerabilities, policy violations, and harmful behaviors before release.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Forcing predictable formats for downstream systems; reduces parsing errors and supports validation/guardrails.

Stores past attention states to speed up autoregressive decoding.

AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.

Learns the score (∇ log p(x)) for generative sampling.

Generative model that learns to reverse a gradual noise process.

Autoencoder using probabilistic latent variables and KL regularization.

Two-network setup where generator fools a discriminator.

Temporal and pitch characteristics of speech.

Generates audio waveforms from spectrograms.

Identifying abrupt changes in data generation.

Model execution path in production.

Increasing performance via more data.

Explicit output constraints (format, tone).

Prompt augmented with retrieved documents.

Enables external computation or lookup.

Differences between training and inference conditions.