{"url":"/task/question-generation","name":"Question Generation","slug":"question-generation","description_markdown":"The goal of **Question Generation** is to generate a valid and fluent question according to a given passage and the target answer. Question Generation can be used in many scenarios, such as automatic tutoring systems, improving the performance of Question Answering models and enabling chatbots to lead a conversation. \r\n\r\n<span class=\"description-source\">Source: [Generating Highly Relevant Questions ](https://arxiv.org/abs/1910.03401)</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":664,"papers_with_code":264,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"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":25,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/question-generation-on-squad11","slug":"question-generation-on-squad11","dataset":"SQuAD1.1","dataset_url":"/dataset/squad","rows_in_archive":13,"metrics":["BLEU-4","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"ERNIE-GENLARGE (beam size=5)","paper_title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","paper_url":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","paper_date":"2020-01-26","arxiv_id":"2001.11314","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py"},{"title":"Sharpiless/Versailles-text-generation-with-paddlepaddle","url":"https://github.com/Sharpiless/Versailles-text-generation-with-paddlepaddle"},{"title":"https-github-com-GiangHoang9912/ernie-gen","url":"https://github.com/https-github-com-GiangHoang9912/ernie-gen"},{"title":"MindSpore-scientific/code-12","url":"https://github.com/MindSpore-scientific/code-12/tree/main/FDDE/train-fine"},{"title":"MindCode-4/code-10","url":"https://github.com/MindCode-4/code-10/tree/main/FDDE/train-fine"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-coco-visual-question","slug":"question-generation-on-coco-visual-question","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","dataset_url":"/dataset/coco","rows_in_archive":4,"metrics":["BLEU-1"],"first_row_in_archive_order":{"model":"MDN","paper_title":"Multimodal Differential Network for Visual Question Generation","paper_url":"/paper/multimodal-differential-network-for-visual","paper_date":"2018-08-12","arxiv_id":"1808.03986","code_links":[{"title":"badripatro/MDN-VQG","url":"https://github.com/badripatro/MDN-VQG"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-grailqa-compositional","slug":"question-generation-on-grailqa-compositional","dataset":"GrailQA-Compositional","dataset_url":"/dataset/grailqa","rows_in_archive":4,"metrics":["METEOR","BLEU","FactSpotter"],"first_row_in_archive_order":{"model":"FactJointGT","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_url":"/paper/factspotter-evaluating-the-factual","paper_date":"2023-10-25","arxiv_id":null,"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-grailqa-iid","slug":"question-generation-on-grailqa-iid","dataset":"GrailQA-IID","dataset_url":"/dataset/grailqa","rows_in_archive":4,"metrics":["BLEU","METEOR","FactSpotter"],"first_row_in_archive_order":{"model":"FactT5B","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_url":"/paper/factspotter-evaluating-the-factual","paper_date":"2023-10-25","arxiv_id":null,"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-grailqa-zero-shot","slug":"question-generation-on-grailqa-zero-shot","dataset":"GrailQA-Zero-Shot","dataset_url":"/dataset/grailqa","rows_in_archive":4,"metrics":["METEOR","bleu","FactSpotter"],"first_row_in_archive_order":{"model":"JointGT","paper_title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","paper_url":"/paper/jointgt-graph-text-joint-representation","paper_date":"2021-06-19","arxiv_id":"2106.10502","code_links":[{"title":"thu-coai/JointGT","url":"https://github.com/thu-coai/JointGT"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-fairytaleqa","slug":"question-generation-on-fairytaleqa","dataset":"FairytaleQA","dataset_url":"/dataset/fairytaleqa","rows_in_archive":3,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"BART fine-tuned on FairytaleQA","paper_title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","paper_url":"/paper/fantastic-questions-and-where-to-find-them-1","paper_date":"2022-03-26","arxiv_id":"2203.13947","code_links":[{"title":"uci-soe/fairytaleqadata","url":"https://github.com/uci-soe/fairytaleqadata"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-weibopolls","slug":"question-generation-on-weibopolls","dataset":"WeiboPolls","dataset_url":"/dataset/weibopolls","rows_in_archive":3,"metrics":["ROUGE-1","ROUGE-L","BLEU-1","BLEU-3"],"first_row_in_archive_order":{"model":"UniPoll","paper_title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","paper_url":"/paper/unipoll-a-unified-social-media-poll","paper_date":"2023-06-12","arxiv_id":"2306.06851","code_links":[{"title":"X1AOX1A/UniPoll","url":"https://github.com/X1AOX1A/UniPoll"}],"syntology":null}},{"leaderboard":"/sota/question-generation-on-natural-questions","slug":"question-generation-on-natural-questions","dataset":"Natural Questions","dataset_url":"/dataset/natural-questions","rows_in_archive":2,"metrics":["QAE","R-QAE"],"first_row_in_archive_order":{"model":"Info-HCVAE","paper_title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","paper_url":"/paper/generating-diverse-and-consistent-qa-pairs","paper_date":"2020-05-28","arxiv_id":"2005.13837","code_links":[{"title":"seanie12/Info-HCVAE","url":"https://github.com/seanie12/Info-HCVAE"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/question-generation-on-squad","slug":"question-generation-on-squad","dataset":"SQuAD","dataset_url":"/dataset/squad","rows_in_archive":2,"metrics":["QAE","R-QAE"],"first_row_in_archive_order":{"model":"Info-HCVAE","paper_title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","paper_url":"/paper/generating-diverse-and-consistent-qa-pairs","paper_date":"2020-05-28","arxiv_id":"2005.13837","code_links":[{"title":"seanie12/Info-HCVAE","url":"https://github.com/seanie12/Info-HCVAE"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/question-generation-on-triviaqa","slug":"question-generation-on-triviaqa","dataset":"TriviaQA","dataset_url":"/dataset/triviaqa","rows_in_archive":2,"metrics":["QAE","R-QAE"],"first_row_in_archive_order":{"model":"Info-HCVAE","paper_title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","paper_url":"/paper/generating-diverse-and-consistent-qa-pairs","paper_date":"2020-05-28","arxiv_id":"2005.13837","code_links":[{"title":"seanie12/Info-HCVAE","url":"https://github.com/seanie12/Info-HCVAE"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/question-generation-on-visual-question","slug":"question-generation-on-visual-question","dataset":"Visual Question Generation","dataset_url":"/dataset/vqg","rows_in_archive":1,"metrics":["BLEU-1"],"first_row_in_archive_order":{"model":"MDN","paper_title":"Multimodal Differential Network for Visual Question Generation","paper_url":"/paper/multimodal-differential-network-for-visual","paper_date":"2018-08-12","arxiv_id":"1808.03986","code_links":[{"title":"badripatro/MDN-VQG","url":"https://github.com/badripatro/MDN-VQG"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/natural-questions","name":"Natural Questions","full_name":"","num_papers_in_archive":1404},{"url":"/dataset/triviaqa","name":"TriviaQA","full_name":"","num_papers_in_archive":953},{"url":"/dataset/ok-vqa","name":"OK-VQA","full_name":"Outside Knowledge Visual Question Answering","num_papers_in_archive":368},{"url":"/dataset/sciq","name":"SciQ","full_name":"SciQ","num_papers_in_archive":183},{"url":"/dataset/squad","name":"SQuAD","full_name":"Stanford Question Answering Dataset","num_papers_in_archive":151},{"url":"/dataset/vqg","name":"VQG","full_name":"Visual Question Generation","num_papers_in_archive":80},{"url":"/dataset/hybridqa","name":"HybridQA","full_name":"","num_papers_in_archive":70},{"url":"/dataset/grailqa","name":"GrailQA","full_name":"Strongly Generalizable Question Answering","num_papers_in_archive":34},{"url":"/dataset/fairytaleqa","name":"FairytaleQA","full_name":"","num_papers_in_archive":26},{"url":"/dataset/ropes","name":"ROPES","full_name":"Reasoning Over Paragraph Effects in Situations","num_papers_in_archive":24},{"url":"/dataset/mmd","name":"MMD","full_name":"Multimodal Dialogs","num_papers_in_archive":18},{"url":"/dataset/freebaseqa","name":"FreebaseQA","full_name":"","num_papers_in_archive":17},{"url":"/dataset/inquisitive","name":"INQUISITIVE","full_name":"","num_papers_in_archive":13},{"url":"/dataset/glge","name":"GLGE","full_name":"General Language Generation Evaluation","num_papers_in_archive":12},{"url":"/dataset/aqua","name":"AQUA","full_name":"","num_papers_in_archive":9},{"url":"/dataset/arid","name":"ARID","full_name":"Autonomous Robot Indoor Dataset","num_papers_in_archive":5},{"url":"/dataset/discq","name":"DiSCQ","full_name":"Discharge Summary Clinical Questions","num_papers_in_archive":4},{"url":"/dataset/clarq","name":"ClarQ","full_name":"ClarQ","num_papers_in_archive":3},{"url":"/dataset/textbox-2-0","name":"TextBox 2.0","full_name":"","num_papers_in_archive":3},{"url":"/dataset/weibopolls","name":"WeiboPolls","full_name":"","num_papers_in_archive":3},{"url":"/dataset/30mqa","name":"30MQA","full_name":"30M Factoid Question-Answer Corpus","num_papers_in_archive":2},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/idk-mrc","name":"IDK-MRC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/infolossqa","name":"InfoLossQA","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/poll-generation","name":"Poll Generation"}],"parent_tasks":[],"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":264,"tagged_in_all":664,"items":[{"url":"/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","arxiv_id":"1910.10683","repositories_listed":57,"syntology":{"n":31,"n_ran":2,"n_unverified":29,"n_pointer_only":0}},{"url":"/paper/diverse-beam-search-decoding-diverse","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","date":"2016-10-07","arxiv_id":"1610.02424","repositories_listed":25,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/diverse-beam-search-decoding-diverse","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","date":"2016-10-07","arxiv_id":"1610.02424","repositories_listed":25,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/learning-to-ask-neural-question-generation","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","date":"2017-04-29","arxiv_id":"1705.00106","repositories_listed":10,"syntology":null},{"url":"/paper/learning-to-ask-neural-question-generation","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","date":"2017-04-29","arxiv_id":"1705.00106","repositories_listed":10,"syntology":null},{"url":"/paper/unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/neural-question-generation-from-text-a","title":"Neural Question Generation from Text: A Preliminary Study","date":"2017-04-06","arxiv_id":"1704.01792","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/neural-question-generation-from-text-a","title":"Neural Question Generation from Text: A Preliminary Study","date":"2017-04-06","arxiv_id":"1704.01792","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","date":"2020-01-26","arxiv_id":"2001.11314","repositories_listed":5,"syntology":null},{"url":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","date":"2020-01-26","arxiv_id":"2001.11314","repositories_listed":5,"syntology":null},{"url":"/paper/prophetnet-predicting-future-n-gram-for","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","date":"2020-01-13","arxiv_id":"2001.04063","repositories_listed":5,"syntology":null},{"url":"/paper/prophetnet-predicting-future-n-gram-for","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","date":"2020-01-13","arxiv_id":"2001.04063","repositories_listed":5,"syntology":null},{"url":"/paper/infinity-mm-scaling-multimodal-performance","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","date":"2024-10-24","arxiv_id":"2410.18558","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/infinity-mm-scaling-multimodal-performance","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","date":"2024-10-24","arxiv_id":"2410.18558","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","repositories_listed":4,"syntology":null},{"url":"/paper/transformer-based-end-to-end-question","title":"Simplifying Paragraph-level Question Generation via Transformer Language Models","date":"2020-05-03","arxiv_id":"2005.01107","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/transformer-based-end-to-end-question","title":"Simplifying Paragraph-level Question Generation via Transformer Language Models","date":"2020-05-03","arxiv_id":"2005.01107","repositories_listed":4,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/synthetic-qa-corpora-generation-with","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","date":"2019-06-12","arxiv_id":"1906.05416","repositories_listed":4,"syntology":null},{"url":"/paper/synthetic-qa-corpora-generation-with","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","date":"2019-06-12","arxiv_id":"1906.05416","repositories_listed":4,"syntology":null},{"url":"/paper/machine-comprehension-by-text-to-text-neural","title":"Machine Comprehension by Text-to-Text Neural Question Generation","date":"2017-05-04","arxiv_id":"1705.02012","repositories_listed":4,"syntology":null},{"url":"/paper/machine-comprehension-by-text-to-text-neural","title":"Machine Comprehension by Text-to-Text Neural Question Generation","date":"2017-05-04","arxiv_id":"1705.02012","repositories_listed":4,"syntology":null},{"url":"/paper/it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","repositories_listed":3,"syntology":null},{"url":"/paper/truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/prophetnet-x-large-scale-pre-training-models","title":"ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation","date":"2021-04-16","arxiv_id":"2104.08006","repositories_listed":3,"syntology":null},{"url":"/paper/prophetnet-x-large-scale-pre-training-models","title":"ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation","date":"2021-04-16","arxiv_id":"2104.08006","repositories_listed":3,"syntology":null},{"url":"/paper/prophetnet-predicting-future-n-gram-for-1","title":"ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training","date":"2020-11-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/prophetnet-predicting-future-n-gram-for-1","title":"ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training","date":"2020-11-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","repositories_listed":3,"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","arxiv_id":"2002.12804","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}],"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"}}