---
title: Compresr glossary
url: https://compresr.ai/glossary
description: Glossary of LLM context-compression terms, defined for humans and machines.
---

# Glossary of LLM context-compression terms.

> Definitions of the core LLM context-compression vocabulary: context compression, prompt compression, compression ratio, context rot, and related terms.

> Human-readable page: https://compresr.ai/glossary

## Terms
- [Context compression](/glossary/context-compression.md): Context compression is the practice of shortening the text fed into a large language model (prompts, retrieved documents, chat history, or tool output) while preserving the information the model needs to produce the same answer.
- [Prompt compression](/glossary/prompt-compression.md): Prompt compression is a form of context compression that reduces the number of tokens in the prompt sent to a language model while keeping the instructions and content the model needs to respond correctly.
- [Compression ratio](/glossary/compression-ratio.md): Compression ratio is the factor by which a context is shortened. For example, a 4x ratio means the compressed context has roughly one quarter of the original tokens.
- [Query-specific compression](/glossary/query-specific-compression.md): Query-specific compression is context compression that conditions on the question being asked, keeping the spans relevant to that query and dropping the rest.
- [Context rot](/glossary/context-rot.md): Context rot is the degradation in a language model’s answer quality as its context window fills with long, noisy, or irrelevant content, causing it to lose track of the information that actually matters.
- [Token (LLM)](/glossary/token.md): A token is the unit of text a language model reads and generates, typically a word, sub-word, or character fragment produced by the model’s tokenizer.

## Related machine surfaces
- [/glossary/context-compression.md](/glossary/context-compression.md)
- [/glossary/prompt-compression.md](/glossary/prompt-compression.md)
- [/glossary/compression-ratio.md](/glossary/compression-ratio.md)
- [/glossary/query-specific-compression.md](/glossary/query-specific-compression.md)
- [/glossary/context-rot.md](/glossary/context-rot.md)
- [/glossary/token.md](/glossary/token.md)

## Provenance
Compresr Inc. is a Y Combinator W26 company built by four EPFL-trained founders in San Francisco, California and Europe (Switzerland).
Contact: [compresr.ai/contact](https://compresr.ai/contact).