Results for "causal generation"

Directed acyclic graph encoding causal relationships.

Formal model linking causal mechanisms and variables.

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

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

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

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

Stochastic generation strategies that trade determinism for diversity; key knobs include temperature and nucleus sampling.

Identifying abrupt changes in data generation.

Training objective where the model predicts the next token given previous tokens (causal modeling).

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Controlled experiment comparing variants by random assignment to estimate causal effects of changes.

Expected causal effect of a treatment.

Variable enabling causal inference despite confounding.

AI proposing scientific hypotheses.

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

Prevents attention to future tokens during training/inference.