The FACTS Grounding Leaderboard

Google FACTS Grounding scores whether long-form answers stay faithful to a supplied document, using an ensemble of LLM judges plus an eligibility filter.

Also known as: FACTS Grounding, FACTS Grounding v1

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorygeneration
Subcategorylong-form answers grounded in a supplied document (up to 32k tokens)
Page statusactive
Metricfinal factuality score (share of responses that are eligible and fully grounded, averaged over three judges)
Directionhigher_is_better
Unit%
Dataset size1719
Dataset licenceCC-BY-4.0
PublisherGoogle DeepMind, Google Research, Google Cloud, and Kaggle

What it measures

FACTS Grounding checks scenario-one factuality: every claim in a long-form answer must be supported by a document in the prompt, not by parametric world knowledge. Each example has a system instruction ("use only this context"), a user request (QA, summary, rewrite) and a web-sourced document up to 32k tokens (mean about 2.5k). The request must be non-trivial and must not need extra-document expertise, maths, or creative writing. This is attribution to provided context, not closed-book factoids and not web search.

Task format

Single-turn generation: system instruction plus user request plus full document. Judges then run two stages, eligibility then span/response-level grounding.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub