Popular Terms

A learned dense vector representation that carries the meaning of a word, document, image, or another entity.

A quantization approach that reduces a pretrained model to lower-bit precision to gain memory and speed benefits.

A multi-label task that predicts which sound events are present in an audio clip at the clip level.

A correction process that brings late-arriving data into alignment with previously produced batch outputs.

An advanced recurrent architecture that uses gating mechanisms to learn long-term dependencies.

A type of metadata showing who uses a data asset, how often, and for what purposes.

An approach in which only relevant expert subnetworks are activated for each input to achieve scale and efficiency.

An approach that enables a model to flag unseen classes as unknown instead of assigning them an overconfident incorrect label.

A version of a general language model adapted to follow task instructions more effectively.

An architectural approach that supports model generation with external knowledge sources to produce more current and grounded answers.

A quantity with direction and magnitude, and one of the most fundamental representations in linear algebra.

A core Document AI task that converts text within images or documents into machine-processable text.

A generative modeling approach that synthesizes new images from natural language prompts.

A model design that processes different data types such as text, images, audio, or video within a shared attention architecture.

A quality approach aimed at making model confidence better aligned with actual correctness.

The ability of a model to avoid fabricating certainty and instead decline or express uncertainty when it is not confident.

A quality dimension describing how well generated content aligns with real-world facts, source data, or verifiable truth.

The phenomenon in which a model generates fluent but unsupported or incorrect content.

An auxiliary model that estimates how preferable generated outputs are and provides signals for alignment.

An alignment approach that tries to guide model behavior through explicit principle sets and normative rules.

A simpler alignment approach that learns directly from preference pairs.

An alignment approach that uses reward signals to make model outputs more consistent with human preferences.

A workflow pattern that attempts to validate model output through additional checks, source review, or second-stage verification.

An approach that improves trust by explicitly showing the source passages supporting the generated answer.