SummEdits

6,348-item binary benchmark asking whether a small edit to a factually consistent summary preserved consistency with its source document, across 10 text domains.

Also known as: SummEdits Benchmark

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.
Categoryreasoning
Subcategorybinary factual-consistency detection between a document and an edited summary, across 10 domains
Page statusactive
Metricbalanced accuracy
Directionhigher_is_better
Unit%
Dataset size6348
Dataset licenceApache License 2.0 (salesforce/factualNLG repository)
PublisherSalesforce Research

What it measures

SummEdits tests factual-consistency detection: given a source document and a summary of it, the model must judge whether the summary remains factually consistent with the document. Every item starts from a summary an annotator has already confirmed is fluent and consistent, then a small, "atomic" edit is applied (originally by ChatGPT) that either preserves consistency or introduces a factual error; a human annotator labels the edited version as consistent or inconsistent, discarding ambiguous ("borderline") cases. The benchmark spans 10 domains -- news, podcasts, legal bill summaries (BillSum), dialogue (SamSum), Shakespeare, scientific-paper abstracts (SciTLDR), meeting summaries (QMSum), financial earnings calls (ECTSum), sales emails, and sales calls -- so it is English text throughout but deliberately not limited to news-style summarization.

Task format

Binary classification: given a document and an edited summary, judge the summary factually consistent or inconsistent with the document.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub