Generation Glossary

Browse 31 generation terms defined in plain English, from the cultural dictionary of computing.

31 Generation Terms

AI Generation
Content or output produced by an AI system, including text, code, images, audio, or structured data. Teams also use the phrase to describe the act of...
AI Image
An image generated, edited, analyzed, or otherwise produced through AI techniques rather than captured or created entirely by traditional means. The term can...
AI Output
The result produced by an AI system, such as text, code, predictions, labels, images, or structured data. Teams evaluate AI output not just for correctness but...
AI Response
The returned output from an AI request, whether as free-form text, structured data, a tool call, or multimodal content. AI responses often need post-processing...
Audio Diffusion
A generative audio approach that learns to denoise signals until realistic sound samples emerge. It influences how models are trained, evaluated, or served,...
Autoregressive Model
A model that generates output one token or step at a time by predicting the next element from the sequence it has already seen.
Controlled Generation
Generation that is constrained by specific requirements such as format, tone, style, factual grounding, or policy rules rather than being left fully...
Denoising Diffusion
A generative process that learns to reverse gradual noise corruption and reconstruct realistic samples. It influences how models are trained, evaluated, or...
Generated Content
Content produced by an AI system rather than written, drawn, or assembled entirely by a person. Generated content can include text, code, images, summaries,...
Generative Search
A search experience in which AI generates synthesized answers or summaries based on retrieved sources instead of only returning ranked links. Generative search...
Grounded Generation
Generation that is explicitly based on supplied evidence, retrieved documents, tool outputs, or verified context rather than relying only on the model's...
Guided Diffusion
A diffusion generation method that steers sampling toward desired classes, prompts, or conditions. It influences how models are trained, evaluated, or served,...
Image-to-Image
A generation task where one image is transformed into another while preserving selected structure or content. It influences how models are trained, evaluated,...
Interleaved Generation
A generation process in which different types of content, reasoning steps, or tool interactions are mixed together rather than produced in one uninterrupted...
Latent Diffusion
A diffusion approach that operates in a compressed latent space instead of directly on pixels. It influences how models are trained, evaluated, or served, and...
Length Penalty
A decoding parameter or scoring adjustment that discourages or encourages longer outputs when selecting among generated sequences. Length penalties are used to...
LLM Completion
A completion or generated output produced by a large language model in response to a prompt. The term often refers specifically to text generation APIs or the...
Model Generation
The output produced by a model, or in some contexts the act of generating that output from a prompt or input. The phrase is broad and typically refers to text,...
Non-Deterministic Output
Output that can vary across repeated runs even when the same input is used, often because of sampling, temperature, system changes, or distributed execution...
Output Length
The length of the content produced by an AI system, often measured in tokens, words, or characters. Output length affects readability, cost, latency, and...
Overgeneration
A failure mode where a model produces more content than necessary, continues beyond the desired stopping point, or adds unsupported elaboration. Overgeneration...
Parallel Generation
Generation strategies or system designs that produce multiple outputs, branches, or partial computations in parallel rather than strictly one sequence at a...
Repetition Penalty
A decoding adjustment that discourages a model from repeating the same tokens, words, or phrases too often during generation. Repetition penalties help reduce...
Response Length
The length of an AI response, often discussed in terms of tokens, words, or user-perceived verbosity. Response length affects cost, latency, readability, and...
Schema-Guided Generation
Generation constrained by an explicit schema so outputs conform to a required structured format such as JSON objects with specific fields. Schema-guided...
Sentence Completion
A generation task where the model is asked to complete a partial sentence in a coherent and contextually appropriate way. Sentence completion is a simple but...
Stop Sequence
A token sequence that tells a generation system where to stop producing output when that sequence appears. Stop sequences are used to control output boundaries...
Structured Generation
Generation constrained to produce output in a defined structure such as JSON, tables, typed fields, or schema-aligned objects rather than free-form text alone....
Token Generation
The step-by-step generation of tokens by a model during inference. Token generation speed and quality shape both latency and the final usefulness of the...
Token Healing
Techniques used to smooth awkward token-boundary behavior, especially when continuing partially written text or handling boundaries that would otherwise...
Token Sampling
The process of selecting output tokens from a probability distribution during generation rather than always taking the single highest-probability choice. Token...

Related Topics