Glossary

The maximum number of tokens a language model can process in a single prompt-response cycle, determining how much text...

A machine learning technique that uses human feedback to fine-tune language models, aligning their outputs with human...

An AI system that autonomously plans, executes multi-step tasks, and interacts with external tools and environments to...

Dense numerical vector representations of text, images, or other data that capture semantic meaning in a...

A neural network architecture that routes each input to a subset of specialized sub-networks ("experts"), enabling...

AI systems that can process, understand, and generate across multiple data types — including text, images, audio, and...

An architecture that augments language model generation with retrieved external documents, reducing hallucination and...

A neural network architecture based on self-attention mechanisms that processes input tokens in parallel, serving as...

A specialized database optimized for storing, indexing, and querying high-dimensional vector embeddings, enabling fast...

A model compression technique that reduces the numerical precision of a neural network's weights from higher-bit...

The practice of connecting AI model outputs to verifiable external sources — such as documents, databases, or real-time...

When an AI model generates plausible-sounding but factually incorrect, fabricated, or unsupported information that is...

The process of further training a pre-trained language model on a smaller, task-specific dataset to specialize its...

A training technique where a smaller "student" model learns to replicate the behavior of a larger "teacher" model,...

A prompting technique that instructs language models to decompose problems into intermediate reasoning steps before...

The process of running a trained AI model to generate predictions or outputs from new inputs, as distinct from the...

The practice of designing and optimizing input instructions to guide language model behavior, output format, and...

The fundamental units of text that language models process, typically representing subword fragments, whole words, or...