NQ-Open

Closed-book short-answer QA on real Google queries from Natural Questions, usually scored by exact match on the public 3,610-item original NQ-Open dev split.

Also known as: NQ-open, nq-open, Natural Questions Open

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.
Categoryknowledge
Subcategoryclosed-book short-answer QA on real Google queries derived from Natural Questions
Page statusactive
Metricexact match (lm-eval exact_match; official NQ-Open also uses EM against answer aliases)
Directionhigher_is_better
Unit%
Dataset size3610
Dataset licenceCC BY-SA 3.0 (nq_open README and Hugging Face card); natural-questions GitHub LICENSE file is Apache-2.0 for the repository
PublisherGoogle Research

What it measures

This id is EleutherAI lm-eval task nq_open and the NQ-Open task of Lee, Chang and Toutanova (ACL 2019). It is not HELM natural_qa and not the 2019 long-answer span-selection competition. Each item is an English question from aggregated Google searches. The model must emit a short answer string with no Wikipedia page in the prompt. Lee et al. keep Natural Questions items that have a short answer of at most five tokens and drop the evidence document. All questions are answerable from English Wikipedia in principle.

Task format

lm-eval generate_until. Prompt "Q: {question}?\nA:" after a few-shot header "Answer these questions:\n\n". Stops at newline, period or comma. Greedy decoding (temperature 0). English text.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub