Datasets › Natural Questions

Natural Questions

Introduced by Tom Kwiatkowski et al. in Natural Questions: a Benchmark for Question Answering Research1 Jan 2019 archive 2025-07-28

The Natural Questions corpus is a question answering dataset containing 307,373 training examples, 7,830 development examples, and 7,842 test examples. Each example is comprised of a google.com query and a corresponding Wikipedia page. Each Wikipedia page has a passage (or long answer) annotated on the page that answers the question and one or more short spans from the annotated passage containing the actual answer. The long and the short answer annotations can however be empty. If they are both empty, then there is no answer on the page at all. If the long answer annotation is non-empty, but the short answer annotation is empty, then the annotated passage answers the question but no explicit short answer could be found. Finally 1% of the documents have a passage annotated with a short answer that is “yes” or “no”, instead of a list of short spans.

Source: A BERT Baseline for the Natural Questions Image Source: https://paperswithcode.com/paper/natural-questions-a-benchmark-for-question/

Benchmarks archive 2025-07-28

All 9 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Open-Domain Question Answering · Natural Questions (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

Papers archive 2025-07-28

papers with a benchmark row: 49 · with a code link: 41 · where Syntology ran a sample: 25 (21 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (25 of 49 with a benchmark row: 21 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 49 of 49 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 1,404. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Search-o1: Agentic Search-Enhanced Large Reasoning Models 2 1 9 Jan 2025 not harvested
BM25S: Orders of magnitude faster lexical search via eager sparse scoring 3 4 4 Jul 2024 official (archive's flag): 10 ran · 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs 0 4 2 Jul 2024 not harvested
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation 1 1 26 Jun 2024 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (3 pointer-only for licence)
Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers 1 2 22 Mar 2024 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
ChatQA: Surpassing GPT-4 on Conversational QA and RAG 0 2 18 Jan 2024 not harvested
Mistral 7B 6 1 10 Oct 2023 official (archive's flag): 9 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
Llama 2: Open Foundation and Fine-Tuned Chat Models 19 1 18 Jul 2023 community repositories only · 33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified (20 pointer-only for licence)
PaLM 2 Technical Report 1 3 17 May 2023 not harvested
LLaMA: Open and Efficient Foundation Language Models 57 4 27 Feb 2023 official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified (4 pointer-only for licence)
REPLUG: Retrieval-Augmented Black-Box Language Models 3 2 30 Jan 2023 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (13 pointer-only for licence)
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer 1 2 5 Dec 2022 not harvested
FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering 0 1 18 Nov 2022 not harvested
Ask Me Anything: A simple strategy for prompting language models 3 3 5 Oct 2022 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
Atlas: Few-shot Learning with Retrieval Augmented Language Models 2 4 5 Aug 2022 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval 1 1 6 Jun 2022 not harvested
PaLM: Scaling Language Modeling with Pathways 7 3 5 Apr 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified
Training Compute-Optimal Large Language Models 2 1 29 Mar 2022 8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (4 pointer-only for licence)
Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation 1 1 15 Mar 2022 not harvested
SGPT: GPT Sentence Embeddings for Semantic Search 1 2 17 Feb 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts 0 3 13 Dec 2021 not harvested
Improving language models by retrieving from trillions of tokens 2 1 8 Dec 2021 16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (3 pointer-only for licence)
Scaling Language Models: Methods, Analysis & Insights from Training Gopher 3 1 8 Dec 2021 not harvested
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? 2 1 13 Oct 2021 not harvested
R2-D2: A Modular Baseline for Open-Domain Question Answering 1 5 8 Sep 2021 not harvested
0.8% Nyquist computational ghost imaging via non-experimental deep learning 0 2 17 Aug 2021 not harvested
Domain-matched Pre-training Tasks for Dense Retrieval 1 1 28 Jul 2021 not harvested
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering 2 2 9 Jun 2021 official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (4 pointer-only for licence)
Efficient Passage Retrieval with Hashing for Open-domain Question Answering 1 2 2 Jun 2021 not harvested
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models 3 2 17 Apr 2021 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
UnitedQA: A Hybrid Approach for Open Domain Question Answering 0 2 1 Jan 2021 not harvested
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering 1 2 29 Dec 2020 not harvested
Learning Dense Representations of Phrases at Scale 4 1 23 Dec 2020 not harvested
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering 1 1 16 Oct 2020 not harvested
Generation-Augmented Retrieval for Open-domain Question Answering 1 1 17 Sep 2020 not harvested
Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding 0 1 13 Sep 2020 not harvested
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering 8 2 2 Jul 2020 not harvested
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval 5 1 1 Jul 2020 official (archive's flag): 10 ran · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs 1 2 28 May 2020 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (3 pointer-only for licence)
Language Models are Few-Shot Learners 67 1 28 May 2020 community repositories only · 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified (7 pointer-only for licence)
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks 18 1 22 May 2020 6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Dense Passage Retrieval for Open-Domain Question Answering 19 2 10 Apr 2020 official: harvested, nothing ran · 11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (9 pointer-only for licence)
REALM: Retrieval-Augmented Language Model Pre-Training 6 1 10 Feb 2020 community repositories only · 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Reformer: The Efficient Transformer 10 1 13 Jan 2020 community repositories only · 6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified
Frustratingly Easy Natural Question Answering 0 1 11 Sep 2019 not harvested
Natural Questions: a Benchmark for Question Answering Research 1 1 1 Jun 2019 not harvested
Generating Long Sequences with Sparse Transformers 7 1 23 Apr 2019 community repositories only · 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
A BERT Baseline for the Natural Questions 3 1 24 Jan 2019 community repositories only · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Reading Wikipedia to Answer Open-Domain Questions 10 1 31 Mar 2017 community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)

Dataset loaders archive 2025-07-28

7 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY-SA 3.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Natural Questions
  • Natural Questions (long)
  • Natural Questions (short)
  • NQ
  • NQ (BEIR)

5 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections