DROP

An adversarially crowdsourced reading-comprehension test requiring numerical and discrete operations -- addition, counting, sorting -- over a paragraph, not just span lookup.

Also known as: DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

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
Subcategoryreading comprehension with discrete reasoning
Page statusactive
MetricF1 (exact match also reported)
Directionhigher_is_better
Unit% F1
Dataset size9535
Dataset licenceCC BY-SA 4.0
PublisherUniversity of California, Irvine; Allen Institute for AI; University of Washington; Hebrew University of Jerusalem

What it measures

DROP gives a model a short English passage -- commonly a Wikipedia paragraph about an NFL game, a census report or a historical event -- and a question that cannot be answered by locating one matching span of text. Answering requires resolving references to multiple positions in the passage and then performing a discrete operation over what is found there: adding or subtracting numbers, counting how many events satisfy a condition, sorting values, or comparing dates. Answers are a number, a date, or one or more short text spans; there are no answer choices.

Task format

Free-response reading comprehension: passage plus question in, a number, a date, or one or more text spans out; no answer choices.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub