ModelRefs / ROUGE — AI Glossary
ROUGE — AI Glossary
A recall-oriented metric measuring n-gram overlap between generated summaries and reference summaries. ROUGE-L is the standard for summarization evaluation.
Overview
ROUGE (Lin 2004) has three main variants: ROUGE-N (n-gram recall), ROUGE-L (longest common subsequence), ROUGE-S (skip-bigram). ROUGE-L is the standard for summarization evaluation. Like BLEU, correlates poorly with human judgment on abstractive summaries. Computed by the `rouge-score` Python library.
Reference details
| Topic | evaluation |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to ROUGE — AI Glossary.
Frequently asked questions
What is ROUGE?
A recall-oriented metric measuring n-gram overlap between generated summaries and reference summaries.
What concepts are related to ROUGE?
Closely related concepts include bleu, bertscore, exact match.