{"url":"/task/natural-questions","name":"Natural Questions","slug":"natural-questions","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":178,"papers_with_code":89,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/natural-questions-on-theoremqa","slug":"natural-questions-on-theoremqa","dataset":"TheoremQA","dataset_url":"/dataset/theoremqa","rows_in_archive":19,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (PoT)","paper_title":"TheoremQA: A Theorem-driven Question Answering dataset","paper_url":"/paper/theoremqa-a-theorem-driven-question-answering","paper_date":"2023-05-21","arxiv_id":"2305.12524","code_links":[{"title":"wenhuchen/theoremqa","url":"https://github.com/wenhuchen/theoremqa"}],"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/natural-questions-on-big-bench","slug":"natural-questions-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=64)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/theoremqa","name":"TheoremQA","full_name":"TheoremQA","num_papers_in_archive":40},{"url":"/dataset/qampari","name":"QAMPARI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/qasports","name":"QASports","full_name":"A Question Answering Dataset about Sports","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/general-knowledge","name":"General Knowledge"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":89,"tagged_in_all":178,"items":[{"url":"/paper/leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","repositories_listed":8,"syntology":null},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","repositories_listed":5,"syntology":null},{"url":"/paper/relevance-guided-supervision-for-openqa-with","title":"Relevance-guided Supervision for OpenQA with ColBERT","date":"2020-07-01","arxiv_id":"2007.00814","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/tempoqr-temporal-question-reasoning-over","title":"TempoQR: Temporal Question Reasoning over Knowledge Graphs","date":"2021-12-10","arxiv_id":"2112.05785","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/autoqa-from-databases-to-qa-semantic-parsers","title":"AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data","date":"2020-10-09","arxiv_id":"2010.04806","repositories_listed":3,"syntology":{"n":26,"n_ran":12,"n_unverified":14,"n_pointer_only":26}},{"url":"/paper/event-extraction-by-answering-almost-natural","title":"Event Extraction by Answering (Almost) Natural Questions","date":"2020-04-28","arxiv_id":"2004.13625","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-bert-baseline-for-the-natural-questions","title":"A BERT Baseline for the Natural Questions","date":"2019-01-24","arxiv_id":"1901.08634","repositories_listed":3,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/lightweight-and-direct-document-relevance","title":"Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval","date":"2025-04-07","arxiv_id":"2504.05181","repositories_listed":2,"syntology":null},{"url":"/paper/dr-spider-a-diagnostic-evaluation-benchmark","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","date":"2023-01-21","arxiv_id":"2301.08881","repositories_listed":2,"syntology":null},{"url":"/paper/dptdr-deep-prompt-tuning-for-dense-passage","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","date":"2022-08-24","arxiv_id":"2208.11503","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/would-you-ask-it-that-way-measuring-and","title":"Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering","date":"2022-05-25","arxiv_id":"2205.12768","repositories_listed":2,"syntology":null},{"url":"/paper/qampari-an-open-domain-question-answering","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","date":"2022-05-25","arxiv_id":"2205.12665","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/continual-learning-with-knowledge-transfer","title":"Continual Learning with Knowledge Transfer for Sentiment Classification","date":"2021-12-18","arxiv_id":"2112.10021","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","arxiv_id":"2007.15207","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","repositories_listed":2,"syntology":null},{"url":"/paper/generating-natural-questions-about-an-image","title":"Generating Natural Questions About an Image","date":"2016-03-19","arxiv_id":"1603.06059","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/constructing-and-evaluating-declarative-rag","title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","date":"2025-06-12","arxiv_id":"2506.10802","repositories_listed":1,"syntology":null},{"url":"/paper/poisonarena-uncovering-competing-poisoning","title":"PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation","date":"2025-05-18","arxiv_id":"2505.12574","repositories_listed":1,"syntology":null},{"url":"/paper/grada-graph-based-reranker-against","title":"GRADA: Graph-based Reranker against Adversarial Documents Attack","date":"2025-05-12","arxiv_id":"2505.07546","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-vs-fine-tuning-a-reproducibility","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","date":"2025-05-12","arxiv_id":"2505.07166","repositories_listed":1,"syntology":null},{"url":"/paper/s1-bench-a-simple-benchmark-for-evaluating","title":"S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models","date":"2025-04-14","arxiv_id":"2504.10368","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}