{"url":"/dataset/webquestions","name":"WebQuestions","full_name":null,"description_markdown":"The **WebQuestions** dataset is a question answering dataset using Freebase as the knowledge base and contains 6,642 question-answer pairs. It was created by crawling questions through the Google Suggest API, and then obtaining answers using Amazon Mechanical Turk. The original split uses 3,778 examples for training and 2,032 for testing. All answers are defined as Freebase entities.\r\n\r\nExample questions (answers) in the dataset include “Where did Edgar Allan Poe died?” (baltimore) or “What degrees did Barack Obama get?” (bachelor_of_arts, juris_doctor).\r\n\r\nSource: [Question Answering with Subgraph Embeddings](https://arxiv.org/abs/1406.3676)\r\nImage Source: [Berant et al](https://www.aclweb.org/anthology/D13-1160)","description_withheld":null,"homepage":"https://worksheets.codalab.org/worksheets/0xba659fe363cb46e7a505c5b6a774dc8a","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/semantic-parsing-on-freebase-from-question","title":"Semantic Parsing on Freebase from Question-Answer Pairs","first_author":"Jonathan Berant","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"KG-to-Text Generation","url":"/task/kg-to-text","datasets_with_task":"/datasets/task/kg-to-text"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WebQuestions"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/web_questions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Stanford/web_questions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/stanfordnlp/web_questions","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#web-questions","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/web_questions","frameworks":["tf","jax"]},{"repo":"https://github.com/RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox/blob/main/docs/utilization/supported-datasets.md","frameworks":["pytorch"]}],"num_papers_in_archive":241,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-webquestions","task":"Question Answering","dataset_variant":"WebQuestions","rows":37,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"CoA","paper":"/paper/chain-of-action-faithful-and-multimodal","metrics":{"EM":"70.7"},"code_links":[{"title":"MAGICS-LAB/Chain-of-Actions","url":"https://github.com/MAGICS-LAB/Chain-of-Actions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/kg-to-text-generation-on-webquestions","task":"KG-to-Text Generation","dataset_variant":"WebQuestions","rows":5,"metrics":["BLEU","METEOR","ROUGE"],"first_row_in_archive_order":{"model":"JointGT (BART)","paper":"/paper/jointgt-graph-text-joint-representation","metrics":{"BLEU":"30.02","METEOR":"32.05","ROUGE":"55.6"},"code_links":[{"title":"thu-coai/JointGT","url":"https://github.com/thu-coai/JointGT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-domain-question-answering-on","task":"Open-Domain Question Answering","dataset_variant":"WebQuestions","rows":4,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"UniK-QA","paper":"/paper/unified-open-domain-question-answering-with","metrics":{"Exact Match":"57.7"},"code_links":[{"title":"facebookresearch/UniK-QA","url":"https://github.com/facebookresearch/UniK-QA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/knowledge-base-question-answering-on-3","task":"Knowledge Base Question Answering","dataset_variant":"WebQuestions","rows":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"PoG-GPT4 (Tan et al., 2024)","paper":"/paper/paths-over-graph-knowledge-graph-enpowered","metrics":{"EM":"84.6"},"code_links":[{"title":"SteveTANTAN/PoG","url":"https://github.com/SteveTANTAN/PoG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","rows_on_this_dataset":9,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":7,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/fido-fusion-in-decoder-optimized-for-stronger","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","date":"2022-12-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fie-building-a-global-probability-space-by","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","date":"2022-11-18","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":15,"samples_unverified":19,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":37,"samples_ran":30,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/glam-efficient-scaling-of-language-models","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","date":"2021-12-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unified-open-domain-question-answering-with","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","date":"2020-12-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","rows_on_this_dataset":4,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":65,"samples_ran":15,"samples_unverified":50,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/toward-subgraph-guided-knowledge-graph","title":"Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks","date":"2020-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dense-passage-retrieval-for-open-domain","title":"Dense Passage Retrieval for Open-Domain Question Answering","date":"2020-04-10","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/realm-retrieval-augmented-language-model-pre","title":"REALM: Retrieval-Augmented Language Model Pre-Training","date":"2020-02-10","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","rows_on_this_dataset":1,"code_links":57,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":2,"samples_unverified":29,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190600300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","date":"2019-06-01","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","rows_on_this_dataset":1,"code_links":21,"syntology":null},{"paper":"/paper/large-scale-simple-question-answering-with","title":"Large-scale Simple Question Answering with Memory Networks","date":"2015-06-05","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/question-answering-with-subgraph-embeddings","title":"Question Answering with Subgraph Embeddings","date":"2014-06-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/open-question-answering-with-weakly","title":"Open Question Answering with Weakly Supervised Embedding Models","date":"2014-04-16","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":14,"samples_harvested":260,"samples_ran":105,"samples_unverified":155,"pointer_only_for_licence":22,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}