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
- Ai (25 terms in common)
- Diffusion (4 terms in common)
- Decoding (3 terms in common)
- Outputs (3 terms in common)
- Responses (2 terms in common)
- Structured Output (2 terms in common)
- Failure Modes (1 terms in common)
- Grounding (1 terms in common)
- Ml (1 terms in common)
- Denoising (1 terms in common)
- Transformation (1 terms in common)
- Images (1 terms in common)
- Determinism (1 terms in common)
- Content (1 terms in common)
- Language Models (1 terms in common)
- Sampling (1 terms in common)
- Llms (1 terms in common)
- Audio (1 terms in common)
- Tokens (1 terms in common)
- Language (1 terms in common)