{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":171,"of_with_code":52,"tagged_in_all":171,"counts":{"archive_papers_tagged":171,"with_a_code_link":52,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":171,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1","slug":"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":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1#ran","syntology_url":"https://syntology.ai/paper/1506.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.08909"}},"official":{"repos":["npow/ubottu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/abcnn-attention-based-convolutional-neural","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}},"official":null}},{"url":"/paper/gated-attention-readers-for-text","slug":"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":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gated-attention-readers-for-text#ran","syntology_url":"https://syntology.ai/paper/1606.01549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01549"}},"official":{"repos":["bdhingra/ga-reader"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/simple-and-effective-text-matching-with-1","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"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","sample_list":"/paper/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}},"official":{"repos":["hitvoice/RE2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-to-rank-question-answer-pairs-using","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ada-leval-evaluating-long-context-llms-with#ran","syntology_url":"https://syntology.ai/paper/2404.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06480"}},"official":{"repos":["open-compass/ada-leval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hgot-hierarchical-graph-of-thoughts-for","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"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","sample_list":"/paper/when-benchmarks-are-targets-revealing-the#ran","syntology_url":"https://syntology.ai/paper/2402.01781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01781"}},"official":{"repos":["national-center-for-ai-saudi-arabia/lm-evaluation-harness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-math-word-problem-with-problem-type","slug":"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","slug":"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","slug":"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","slug":"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_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leveraging-large-language-models-for-multiple#ran","syntology_url":"https://syntology.ai/paper/2210.12353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12353"}},"official":{"repos":["byu-pccl/leveraging-llms-for-mcqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/once-is-enough-a-light-weight-cross-attention","slug":"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/evaluating-coreference-resolvers-on-community","slug":"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/reducing-spurious-correlations-for-answer","slug":"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/paragraph-based-transformer-pre-training-for","slug":"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","slug":"solution-of-debertav3-on-commonsenseqa","title":"Solution of DeBERTaV3 on CommonsenseQA","date":"2022-04-30","arxiv_id":"2206.05033","repositories_listed":1,"syntology":null},{"url":"/paper/cicero-a-dataset-for-contextualized","slug":"cicero-a-dataset-for-contextualized","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","date":"2022-03-25","arxiv_id":"2203.13926","repositories_listed":1,"syntology":null},{"url":"/paper/re-improving-multi-hop-question-answering","slug":"re-improving-multi-hop-question-answering","title":"[Re] Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","date":"2021-01-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comqa-compositional-question-answering-via","slug":"comqa-compositional-question-answering-via","title":"ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks","date":"2021-01-16","arxiv_id":"2101.06400","repositories_listed":1,"syntology":null},{"url":"/paper/nut-rc-noisy-user-generated-text-oriented","slug":"nut-rc-noisy-user-generated-text-oriented","title":"NUT-RC: Noisy User-generated Text-oriented Reading Comprehension","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-bidirectional-encoder","slug":"utilizing-bidirectional-encoder","title":"Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection","date":"2020-11-14","arxiv_id":"2011.07208","repositories_listed":1,"syntology":null},{"url":"/paper/a-wrong-answer-or-a-wrong-question-an","slug":"a-wrong-answer-or-a-wrong-question-an","title":"A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering","date":"2020-10-13","arxiv_id":"2010.06835","repositories_listed":1,"syntology":null},{"url":"/paper/multicqa-zero-shot-transfer-of-self","slug":"multicqa-zero-shot-transfer-of-self","title":"MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale","date":"2020-10-02","arxiv_id":"2010.00980","repositories_listed":1,"syntology":null},{"url":"/paper/contextualized-embeddings-based-transformer","slug":"contextualized-embeddings-based-transformer","title":"Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/review-guided-helpful-answer-identification","slug":"review-guided-helpful-answer-identification","title":"Review-guided Helpful Answer Identification in E-commerce","date":"2020-03-13","arxiv_id":"2003.06209","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-answer-selection-and-answer","slug":"joint-learning-of-answer-selection-and-answer","title":"Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering","date":"2019-11-22","arxiv_id":"1911.09801","repositories_listed":1,"syntology":null},{"url":"/paper/neural-duplicate-question-detection-without-1","slug":"neural-duplicate-question-detection-without-1","title":"Neural Duplicate Question Detection without Labeled Training Data","date":"2019-11-13","arxiv_id":"1911.05594","repositories_listed":1,"syntology":null},{"url":"/paper/a-gated-self-attention-memory-network-for","slug":"a-gated-self-attention-memory-network-for","title":"A Gated Self-attention Memory Network for Answer Selection","date":"2019-09-13","arxiv_id":"1909.09696","repositories_listed":1,"syntology":null},{"url":"/paper/propagate-selector-detecting-supporting","slug":"propagate-selector-detecting-supporting","title":"Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks","date":"2019-08-24","arxiv_id":"1908.09137","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-attention-with-keyword-mask-model","slug":"sequential-attention-with-keyword-mask-model","title":"Sequential Attention with Keyword Mask Model for Community-based Question Answering","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bertsel-answer-selection-with-pre-trained","slug":"bertsel-answer-selection-with-pre-trained","title":"BERTSel: Answer Selection with Pre-trained Models","date":"2019-05-18","arxiv_id":"1905.07588","repositories_listed":1,"syntology":null},{"url":"/paper/recurrently-controlled-recurrent-networks","slug":"recurrently-controlled-recurrent-networks","title":"Recurrently Controlled Recurrent Networks","date":"2018-11-24","arxiv_id":"1811.09786","repositories_listed":1,"syntology":null},{"url":"/paper/document-modeling-with-external-attention-for","slug":"document-modeling-with-external-attention-for","title":"Document Modeling with External Attention for Sentence Extraction","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/question-condensing-networks-for-answer","slug":"question-condensing-networks-for-answer","title":"Question Condensing Networks for Answer Selection in Community Question Answering","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iit-uhh-at-semeval-2017-task-3-exploring","slug":"iit-uhh-at-semeval-2017-task-3-exploring","title":"IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification","date":"2017-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/representation-learning-for-answer-selection","slug":"representation-learning-for-answer-selection","title":"Representation Learning for Answer Selection with LSTM-Based Importance Weighting","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-memory-networks-for-answer","slug":"hierarchical-memory-networks-for-answer","title":"Hierarchical Memory Networks for Answer Selection on Unknown Words","date":"2016-09-28","arxiv_id":"1609.08843","repositories_listed":1,"syntology":null},{"url":"/paper/m2s-net-multi-modal-similarity-metric","slug":"m2s-net-multi-modal-similarity-metric","title":"M$^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection","date":"2016-04-19","arxiv_id":"1604.05519","repositories_listed":1,"syntology":null},{"url":null,"slug":"enhancing-mathematical-reasoning-in-large","title":"Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection","date":"2025-04-13","arxiv_id":"2504.09440","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-answer-reranking-strategies-in","title":"Evaluating Answer Reranking Strategies in Time-sensitive Question Answering","date":"2025-03-06","arxiv_id":"2503.04972","repositories_listed":0,"syntology":null},{"url":null,"slug":"fans-formal-answer-selection-for-natural","title":"FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4","date":"2025-03-05","arxiv_id":"2503.03238","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-end-to-end-spoken-question","title":"Zero-Shot End-To-End Spoken Question Answering In Medical Domain","date":"2024-06-09","arxiv_id":"2406.05876","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-answer-selection-in-community","title":"Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models","date":"2023-11-29","arxiv_id":"2311.17502","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-llms-on-document-based-qa-exact","title":"Evaluating LLMs on Document-Based QA: Exact Answer Selection and Numerical Extraction using Cogtale dataset","date":"2023-11-14","arxiv_id":"2311.07878","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-zero-shot-reader-by-reducing","title":"Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering","date":"2023-10-26","arxiv_id":"2310.17490","repositories_listed":0,"syntology":null},{"url":null,"slug":"square-automatic-question-answering","title":"SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References","date":"2023-09-21","arxiv_id":"2309.12250","repositories_listed":0,"syntology":null},{"url":null,"slug":"intent-calibrated-self-training-for-answer","title":"Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues","date":"2023-07-13","arxiv_id":"2307.06703","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-then-select-open-ended-visual","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","date":"2023-05-30","arxiv_id":"2305.18842","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-prompt-experts-for-generalizable","title":"Getting MoRE out of Mixture of Language Model Reasoning Experts","date":"2023-05-24","arxiv_id":"2305.14628","repositories_listed":0,"syntology":null},{"url":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"rlas-biabc-a-reinforcement-learning-based","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","date":"2023-01-07","arxiv_id":"2301.02807","repositories_listed":0,"syntology":null},{"url":null,"slug":"original-content-is-all-you-need-an-empirical","title":"Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-hybrid-semantics-of-relation-paths","title":"Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering Over Knowledge Graphs","date":"2022-09-02","arxiv_id":"2209.00870","repositories_listed":0,"syntology":null},{"url":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","repositories_listed":0,"syntology":null},{"url":"/paper/deim-an-effective-deep-encoding-and","slug":"deim-an-effective-deep-encoding-and","title":"DEIM: An effective deep encoding and interaction model for sentence matching","date":"2022-03-20","arxiv_id":"2203.10482","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answer-sentence-graph-for-joint","title":"Question-Answer Sentence Graph for Joint Modeling Answer Selection","date":"2022-02-16","arxiv_id":"2203.03549","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-retrieval-and-ranking-for-accurate","title":"Double Retrieval and Ranking for Accurate Question Answering","date":"2022-01-16","arxiv_id":"2201.05981","repositories_listed":0,"syntology":null},{"url":null,"slug":"openqa-hybrid-qa-system-relying-on-structured","title":"OpenQA: Hybrid QA System Relying on Structured Knowledge Base as well as Non-structured Data","date":"2021-12-31","arxiv_id":"2112.15356","repositories_listed":0,"syntology":null},{"url":"/paper/percqa-persian-community-question-answering","slug":"percqa-persian-community-question-answering","title":"PerCQA: Persian Community Question Answering Dataset","date":"2021-12-25","arxiv_id":"2112.13238","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-augmented-learning-to-rank-for-querying","title":"Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph","date":"2021-11-20","arxiv_id":"2111.10541","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-emotional-comfort-framework-for-improving","title":"An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service Chatbots","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"if-you-want-to-go-far-go-together","title":"If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-size-neural-network-with-attention","title":"A Multi-Size Neural Network with Attention Mechanism for Answer Selection","date":"2021-04-24","arxiv_id":"2105.03278","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-question-answering-model-robustness","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","date":"2021-04-18","arxiv_id":"2104.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"asbert-siamese-and-triplet-network-embedding","title":"ASBERT: Siamese and Triplet network embedding for open question answering","date":"2021-04-17","arxiv_id":"2104.08558","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-knowledge-aware-attentive","title":"Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge","date":"2021-04-12","arxiv_id":"2104.05216","repositories_listed":0,"syntology":null},{"url":"/paper/keep-learning-self-supervised-meta-learning","slug":"keep-learning-self-supervised-meta-learning","title":"Keep Learning: Self-supervised Meta-learning for Learning from Inference","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-ranking-for-answer-selection","title":"Hierarchical Ranking for Answer Selection","date":"2021-02-01","arxiv_id":"2102.00677","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-wordnet-synset-and-hypernym","title":"Exploiting WordNet Synset and Hypernym Representations for Answer Selection","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explanationlp-abductive-reasoning-for","title":"ExplanationLP: Abductive Reasoning for Explainable Science Question Answering","date":"2020-10-25","arxiv_id":"2010.13128","repositories_listed":0,"syntology":null},{"url":null,"slug":"ms-ranker-accumulating-evidence-from","title":"MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection","date":"2020-10-10","arxiv_id":"2010.04970","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-cls-through-ranking-by-generation","title":"Beyond [CLS] through Ranking by Generation","date":"2020-10-06","arxiv_id":"2010.03073","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-choice-dialogue-based-reading","title":"Knowledgeable Dialogue Reading Comprehension on Key Turns","date":"2020-04-29","arxiv_id":"2004.13988","repositories_listed":0,"syntology":null},{"url":null,"slug":"matching-text-with-deep-mutual-information","title":"Matching Text with Deep Mutual Information Estimation","date":"2020-03-09","arxiv_id":"2003.11521","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-attentive-learning-for","title":"Knowledge-Enhanced Attentive Learning for Answer Selection in Community Question Answering Systems","date":"2019-12-17","arxiv_id":"1912.07915","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-ai-generate-love-advice-toward-neural","title":"Can AI Generate Love Advice?: Toward Neural Answer Generation for Non-Factoid Questions","date":"2019-12-06","arxiv_id":"1912.10163","repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2015-task-3-answer-selection-in-1","title":"SemEval-2015 Task 3: Answer Selection in Community Question Answering","date":"2019-11-26","arxiv_id":"1911.11403","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-induced-multi-relational-framework-for","title":"An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms","date":"2019-11-16","arxiv_id":"1911.06957","repositories_listed":0,"syntology":null},{"url":null,"slug":"bas-an-answer-selection-method-using-bert","title":"BAS: An Answer Selection Method Using BERT Language Model","date":"2019-11-04","arxiv_id":"1911.01528","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-answer-selection-and-answer","title":"Improving Answer Selection and Answer Triggering using Hard Negatives","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-analogy-preserving-sentence","title":"Learning Analogy-Preserving Sentence Embeddings for Answer Selection","date":"2019-10-11","arxiv_id":"1910.05315","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-pairwise-multi-perspective","title":"Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering","date":"2019-09-03","arxiv_id":"1909.01059","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-improvement-of-a-question","title":"Incremental Improvement of a Question Answering System by Re-ranking Answer Candidates using Machine Learning","date":"2019-08-27","arxiv_id":"1908.10149","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automating-healthcare-question","title":"Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"190600156","title":"Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems","date":"2019-06-01","arxiv_id":"1906.00156","repositories_listed":0,"syntology":null},{"url":"/paper/a-compare-aggregate-model-with-latent","slug":"a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","arxiv_id":"1905.12897","repositories_listed":0,"syntology":null},{"url":null,"slug":"gated-group-self-attention-for-answer","title":"Gated Group Self-Attention for Answer Selection","date":"2019-05-26","arxiv_id":"1905.10720","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/answer-selection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/answer-selection/papers/2","json":"/task/answer-selection/papers/2.json","rows":71},{"order":"ran","page":1,"of":1,"url":"/task/answer-selection/papers/ran/1","json":"/task/answer-selection/papers/ran/1.json","rows":7}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"2d8cff2e77d5a214ea7711f5500119b037c870b8cb2ea90cb7aac59cae12d03a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}