SCROLLS (Standardized CompaRison Over Long Language Sequences)

Tel Aviv University suite of seven long-text English tasks (summarisation, QA, NLI) that require synthesising information across naturally long documents.

Also known as: SCROLLS, Standardized CompaRison Over Long Language Sequences, tau/scrolls

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.
Categorylong-context
Subcategoryseven English long-document summarisation, QA, and NLI tasks in one text-to-text format
Page statusactive
MetricSCROLLS aggregate (geometric mean of per-task scores); task metrics ROUGE / F1 / EM
Directionhigher_is_better
Dataset size119495
Dataset licenceMIT
PublisherTel Aviv University NLP (TAU NLP)

What it measures

SCROLLS tests whether a model can synthesise information over texts that are long in the wild, not padded sentences. Seven existing datasets are rewritten as one input-output string: GovReport and SummScreenFD summarisation, QMSum query-based meeting summarisation, Qasper and NarrativeQA question answering, QuALITY four-way long-document QA, and ContractNLI over NDAs. Queries are prepended to the document with a blank line. The intended skill is long-range reading, not short-passage overlap.

Task format

Unified sequence-to-sequence. Official scoring uses a hidden test set on the SCROLLS evaluator. lm-eval loads only train and validation from tau/scrolls zip JSONL (has_test_docs is false) and reformulates causal models with a Question/Answer prompt. QuALITY and ContractNLI are scored as log-likelihood multiple choice in lm-eval; the others generate until a newline.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub