{"url":"/task/answer-selection","name":"Answer Selection","slug":"answer-selection","description_markdown":"**Answer Selection** is the task of identifying the correct answer to a question from a pool of candidate answers. This task can be formulated as a classification or a ranking problem.\n\n\n<span class=\"description-source\">Source: [Learning Analogy-Preserving Sentence Embeddings for Answer Selection ](https://arxiv.org/abs/1910.05315)</span>","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":171,"papers_with_code":52,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":10,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/answer-selection-on-asnq","slug":"answer-selection-on-asnq","dataset":"ASNQ","dataset_url":"/dataset/asnq","rows_in_archive":3,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"DeBERTa-V3-Large + SSP","paper_title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","paper_url":"/paper/pre-training-transformer-models-with-sentence","paper_date":"2022-05-20","arxiv_id":"2205.10455","code_links":[],"syntology":null}},{"leaderboard":"/sota/answer-selection-on-cicero","slug":"answer-selection-on-cicero","dataset":"CICERO","dataset_url":"/dataset/cicero","rows_in_archive":2,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"T5-large","paper_title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","paper_url":"/paper/cicero-a-dataset-for-contextualized","paper_date":"2022-03-25","arxiv_id":"2203.13926","code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}],"syntology":null}},{"leaderboard":"/sota/answer-selection-on-ubuntu-dialogue-v2","slug":"answer-selection-on-ubuntu-dialogue-v2","dataset":"Ubuntu Dialogue (v2, Ranking)","dataset_url":"/dataset/ubuntu-dialogue-corpus","rows_in_archive":2,"metrics":["1 in 10 R@1","1 in 10 R@2","1 in 10 R@5","1 in 2 R@1"],"first_row_in_archive_order":{"model":"BERT + Keep Learning","paper_title":"Keep Learning: Self-supervised Meta-learning for Learning from Inference","paper_url":"/paper/keep-learning-self-supervised-meta-learning","paper_date":"2021-04-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/answer-selection-on-trecqa-1","slug":"answer-selection-on-trecqa-1","dataset":"TrecQA","dataset_url":"/dataset/trecqa","rows_in_archive":1,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"RLAS-BIABC","paper_title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","paper_url":"/paper/rlas-biabc-a-reinforcement-learning-based","paper_date":"2023-01-07","arxiv_id":"2301.02807","code_links":[],"syntology":null}},{"leaderboard":"/sota/answer-selection-on-ubuntu-dialogue-v1","slug":"answer-selection-on-ubuntu-dialogue-v1","dataset":"Ubuntu Dialogue (v1, Ranking)","dataset_url":"/dataset/ubuntu-dialogue-corpus","rows_in_archive":1,"metrics":["1 in 10 R@1","1 in 10 R@2","1 in 10 R@5","1 in 2 R@1"],"first_row_in_archive_order":{"model":"HRDE-LTC","paper_title":"Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering","paper_url":"/paper/learning-to-rank-question-answer-pairs-using","paper_date":"2017-10-10","arxiv_id":"1710.03430","code_links":[{"title":"david-yoon/QA_HRDE_LTC","url":"https://github.com/david-yoon/QA_HRDE_LTC"},{"title":"younggns/comparative-abusive-lang","url":"https://github.com/younggns/comparative-abusive-lang"},{"title":"aus10powell/Automated-Health-Responses","url":"https://github.com/aus10powell/Automated-Health-Responses"}],"syntology":null}},{"leaderboard":"/sota/answer-selection-on-wikiqa-1","slug":"answer-selection-on-wikiqa-1","dataset":"WikiQA","dataset_url":"/dataset/wikiqa","rows_in_archive":1,"metrics":["MAP "],"first_row_in_archive_order":{"model":"RLAS-BIABC","paper_title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","paper_url":"/paper/rlas-biabc-a-reinforcement-learning-based","paper_date":"2023-01-07","arxiv_id":"2301.02807","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/wikiqa","name":"WikiQA","full_name":"Wikipedia open-domain Question Answering","num_papers_in_archive":196},{"url":"/dataset/trecqa","name":"TrecQA","full_name":"Text Retrieval Conference Question Answering","num_papers_in_archive":73},{"url":"/dataset/ubuntu-dialogue-corpus","name":"UDC","full_name":"Ubuntu Dialogue Corpus","num_papers_in_archive":46},{"url":"/dataset/insuranceqa","name":"InsuranceQA","full_name":"","num_papers_in_archive":38},{"url":"/dataset/asnq","name":"ASNQ","full_name":"Answer Sentence Natural Questions","num_papers_in_archive":25},{"url":"/dataset/cicero","name":"CICERO","full_name":"Contextualized Commonsense Inference in Dialogues","num_papers_in_archive":12},{"url":"/dataset/selqa","name":"SelQA","full_name":"","num_papers_in_archive":9},{"url":"/dataset/wikihowqa","name":"WikiHowQA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/milkqa","name":"MilkQA","full_name":"","num_papers_in_archive":2},{"url":"/dataset/wikiqaar","name":"WikiQAar","full_name":"English-Arabic Wikipedia Question-Answering","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":52,"tagged_in_all":171,"items":[{"url":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","date":"2015-06-30","arxiv_id":"1506.08909","repositories_listed":21,"syntology":{"n":26,"n_ran":1,"n_unverified":25,"n_pointer_only":1}},{"url":"/paper/abcnn-attention-based-convolutional-neural","title":"ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs","date":"2015-12-16","arxiv_id":"1512.05193","repositories_listed":8,"syntology":null},{"url":"/paper/neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/gated-attention-readers-for-text","title":"Gated-Attention Readers for Text Comprehension","date":"2016-06-05","arxiv_id":"1606.01549","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-to-rank-question-answer-pairs-using","title":"Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering","date":"2017-10-10","arxiv_id":"1710.03430","repositories_listed":3,"syntology":null},{"url":"/paper/attentive-pooling-networks","title":"Attentive Pooling Networks","date":"2016-02-11","arxiv_id":"1602.03609","repositories_listed":3,"syntology":null},{"url":"/paper/raven-s-progressive-matrices-completion-with","title":"Raven's Progressive Matrices Completion with Latent Gaussian Process Priors","date":"2021-03-22","arxiv_id":"2103.12045","repositories_listed":2,"syntology":null},{"url":"/paper/improving-multi-hop-question-answering-over","title":"Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-learning-with-multi-view-attention","title":"Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering","date":"2018-12-06","arxiv_id":"1812.02354","repositories_listed":2,"syntology":null},{"url":"/paper/a-compare-aggregate-model-for-matching-text","title":"A Compare-Aggregate Model for Matching Text Sequences","date":"2016-11-06","arxiv_id":"1611.01747","repositories_listed":2,"syntology":null},{"url":"/paper/learning-recurrent-span-representations-for","title":"Learning Recurrent Span Representations for Extractive Question Answering","date":"2016-11-04","arxiv_id":"1611.01436","repositories_listed":2,"syntology":null},{"url":"/paper/lstm-based-deep-learning-models-for-non","title":"LSTM-based Deep Learning Models for Non-factoid Answer Selection","date":"2015-11-12","arxiv_id":"1511.04108","repositories_listed":2,"syntology":null},{"url":"/paper/applying-deep-learning-to-answer-selection-a","title":"Applying Deep Learning to Answer Selection: A Study and An Open Task","date":"2015-08-07","arxiv_id":"1508.01585","repositories_listed":2,"syntology":null},{"url":"/paper/finbert-qa-financial-question-answering-with","title":"FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models","date":"2025-04-24","arxiv_id":"2505.00725","repositories_listed":1,"syntology":null},{"url":"/paper/could-thinking-multilingually-empower-llm","title":"Could Thinking Multilingually Empower LLM Reasoning?","date":"2025-04-16","arxiv_id":"2504.11833","repositories_listed":1,"syntology":null},{"url":"/paper/syntqa-synergistic-table-based-question","title":"SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA","date":"2024-09-25","arxiv_id":"2409.16682","repositories_listed":1,"syntology":null},{"url":"/paper/aggregation-of-reasoning-a-hierarchical","title":"Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models","date":"2024-05-21","arxiv_id":"2405.12939","repositories_listed":1,"syntology":null},{"url":"/paper/ada-leval-evaluating-long-context-llms-with","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","date":"2024-04-09","arxiv_id":"2404.06480","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/hgot-hierarchical-graph-of-thoughts-for","title":"HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation","date":"2024-02-14","arxiv_id":"2402.09390","repositories_listed":1,"syntology":null},{"url":"/paper/when-benchmarks-are-targets-revealing-the","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","date":"2024-02-01","arxiv_id":"2402.01781","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/solving-math-word-problem-with-problem-type","title":"Solving Math Word Problem with Problem Type Classification","date":"2023-08-26","arxiv_id":"2308.13844","repositories_listed":1,"syntology":null},{"url":"/paper/abstracting-concept-changing-rules-for","title":"Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems","date":"2023-07-15","arxiv_id":"2307.07734","repositories_listed":1,"syntology":null},{"url":"/paper/realistic-conversational-question-answering","title":"Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement","date":"2023-02-10","arxiv_id":"2302.05137","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-multiple","title":"Leveraging Large Language Models for Multiple Choice Question Answering","date":"2022-10-22","arxiv_id":"2210.12353","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/once-is-enough-a-light-weight-cross-attention","title":"Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling","date":"2022-10-11","arxiv_id":"2210.05261","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-spurious-correlations-for-answer","title":"Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-coreference-resolvers-on-community","title":"Evaluating Coreference Resolvers on Community-based Question Answering: From Rule-based to State of the Art","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","repositories_listed":1,"syntology":null},{"url":"/paper/solution-of-debertav3-on-commonsenseqa","title":"Solution of DeBERTaV3 on CommonsenseQA","date":"2022-04-30","arxiv_id":"2206.05033","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}