{"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/conversational-question-answering","name":"Conversational Question Answering","slug":"conversational-question-answering","description_markdown":null,"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":142,"papers_with_code":63,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/conversational-question-answering-on","slug":"conversational-question-answering-on","dataset":"ConvFinQA","dataset_url":"/dataset/convfinqa","rows_in_archive":2,"metrics":["Execution Accuracy","Program Accuracy"],"first_row_in_archive_order":{"model":"APOLLO","paper_title":"APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning","paper_url":"/paper/apollo-an-optimized-training-approach-for","paper_date":"2022-12-14","arxiv_id":"2212.07249","code_links":[{"title":"gasolsun36/iter-cot","url":"https://github.com/gasolsun36/iter-cot"},{"title":"gasolsun36/dynamicrag","url":"https://github.com/gasolsun36/dynamicrag"},{"title":"gasolsun36/apollo","url":"https://github.com/gasolsun36/apollo"}],"syntology":null}}],"datasets":[{"url":"/dataset/coqa","name":"CoQA","full_name":"Conversational Question Answering Challenge","num_papers_in_archive":281},{"url":"/dataset/quac","name":"QuAC","full_name":"Question Answering in Context","num_papers_in_archive":178},{"url":"/dataset/canard","name":"CANARD","full_name":"A Dataset for Question-in-Context Rewriting","num_papers_in_archive":58},{"url":"/dataset/convfinqa","name":"ConvFinQA","full_name":"Conversational Finance Question Answering","num_papers_in_archive":38},{"url":"/dataset/doc2dial-1","name":"Doc2Dial","full_name":"Doc2Dial: Document-grounded Dialogue","num_papers_in_archive":36},{"url":"/dataset/multidoc2dial","name":"MultiDoc2Dial","full_name":"MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents","num_papers_in_archive":26},{"url":"/dataset/doqa","name":"DoQA","full_name":"","num_papers_in_archive":18},{"url":"/dataset/alpaca-data-galician","name":"Alpaca Data Galician","full_name":"Alpaca Data Galician","num_papers_in_archive":1},{"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/uit-vicoqa","name":"UIT-ViCoQA","full_name":"Conversational machine reading comprehension in the Vietnamese language","num_papers_in_archive":1}],"subtasks":[{"url":"/task/question-rewriting","name":"Question Rewriting"}],"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":142,"of_with_code":63,"tagged_in_all":142,"counts":{"archive_papers_tagged":142,"with_a_code_link":63,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":142,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/sdnet-contextualized-attention-based-deep","slug":"sdnet-contextualized-attention-based-deep","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","date":"2018-12-10","arxiv_id":"1812.03593","repositories_listed":6,"syntology":null},{"url":"/paper/coqa-a-conversational-question-answering","slug":"coqa-a-conversational-question-answering","title":"CoQA: A Conversational Question Answering Challenge","date":"2018-08-21","arxiv_id":"1808.07042","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coqa-a-conversational-question-answering#ran","syntology_url":"https://syntology.ai/paper/1808.07042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.07042"}},"official":null}},{"url":"/paper/query-enhanced-knowledge-intensive","slug":"query-enhanced-knowledge-intensive","title":"Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling","date":"2022-12-19","arxiv_id":"2212.09588","repositories_listed":3,"syntology":null},{"url":"/paper/apollo-an-optimized-training-approach-for","slug":"apollo-an-optimized-training-approach-for","title":"APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning","date":"2022-12-14","arxiv_id":"2212.07249","repositories_listed":3,"syntology":null},{"url":"/paper/plato-pre-trained-dialogue-generation-model","slug":"plato-pre-trained-dialogue-generation-model","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","date":"2019-10-17","arxiv_id":"1910.07931","repositories_listed":3,"syntology":null},{"url":"/paper/pcoqa-persian-conversational-question","slug":"pcoqa-persian-conversational-question","title":"PCoQA: Persian Conversational Question Answering Dataset","date":"2023-12-07","arxiv_id":"2312.04362","repositories_listed":2,"syntology":null},{"url":"/paper/pixiu-a-large-language-model-instruction-data","slug":"pixiu-a-large-language-model-instruction-data","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","date":"2023-06-08","arxiv_id":"2306.05443","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pixiu-a-large-language-model-instruction-data#ran","syntology_url":"https://syntology.ai/paper/2306.05443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05443"}},"official":{"repos":["chancefocus/pixiu"],"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/kl-divergence-guided-temperature-sampling","slug":"kl-divergence-guided-temperature-sampling","title":"KL-Divergence Guided Temperature Sampling","date":"2023-06-02","arxiv_id":"2306.01286","repositories_listed":2,"syntology":null},{"url":"/paper/ditch-the-gold-standard-re-evaluating-1","slug":"ditch-the-gold-standard-re-evaluating-1","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","date":"2021-12-16","arxiv_id":"2112.08812","repositories_listed":2,"syntology":null},{"url":"/paper/easytransfer-a-simple-and-scalable-deep","slug":"easytransfer-a-simple-and-scalable-deep","title":"EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications","date":"2020-11-18","arxiv_id":"2011.09463","repositories_listed":2,"syntology":null},{"url":"/paper/open-domain-question-answering-goes","slug":"open-domain-question-answering-goes","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","date":"2020-10-10","arxiv_id":"2010.04898","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-domain-question-answering-goes#ran","syntology_url":"https://syntology.ai/paper/2010.04898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04898"}},"official":{"repos":["apple/ml-qrecc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/attentive-history-selection-for","slug":"attentive-history-selection-for","title":"Attentive History Selection for Conversational Question Answering","date":"2019-08-26","arxiv_id":"1908.09456","repositories_listed":2,"syntology":null},{"url":"/paper/preference-based-learning-with-retrieval","slug":"preference-based-learning-with-retrieval","title":"Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering","date":"2025-03-28","arxiv_id":"2503.22303","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-task-oriented-dialogues-with-state","slug":"simulating-task-oriented-dialogues-with-state","title":"Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models","date":"2024-04-23","arxiv_id":"2404.14772","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-training-by-synthetic-question","slug":"consistency-training-by-synthetic-question","title":"Consistency Training by Synthetic Question Generation for Conversational Question Answering","date":"2024-04-17","arxiv_id":"2404.11109","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/consistency-training-by-synthetic-question#ran","syntology_url":"https://syntology.ai/paper/2404.11109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11109"}},"official":{"repos":["hamedhematian/syncqg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/normy-non-uniform-history-modeling-for-open","slug":"normy-non-uniform-history-modeling-for-open","title":"NORMY: Non-Uniform History Modeling for Open Retrieval Conversational Question Answering","date":"2024-02-07","arxiv_id":"2402.04548","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-large-language-models-in-semantic","slug":"evaluating-large-language-models-in-semantic","title":"Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs","date":"2024-01-03","arxiv_id":"2401.01711","repositories_listed":1,"syntology":null},{"url":"/paper/let-the-llms-talk-simulating-human-to-human","slug":"let-the-llms-talk-simulating-human-to-human","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","date":"2023-12-05","arxiv_id":"2312.02913","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-question-rewriting-1","slug":"on-the-robustness-of-question-rewriting-1","title":"On the Robustness of Question Rewriting Systems to Questions of Varying Hardness","date":"2023-11-12","arxiv_id":"2311.06807","repositories_listed":1,"syntology":null},{"url":"/paper/glamm-pixel-grounding-large-multimodal-model","slug":"glamm-pixel-grounding-large-multimodal-model","title":"GLaMM: Pixel Grounding Large Multimodal Model","date":"2023-11-06","arxiv_id":"2311.03356","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glamm-pixel-grounding-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2311.03356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03356"}},"official":{"repos":["mbzuai-oryx/groundingLMM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/no-that-s-not-what-i-meant-handling-third","slug":"no-that-s-not-what-i-meant-handling-third","title":"No that's not what I meant: Handling Third Position Repair in Conversational Question Answering","date":"2023-07-31","arxiv_id":"2307.16689","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-retrieval-for-open-domain","slug":"phrase-retrieval-for-open-domain","title":"Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning","date":"2023-06-07","arxiv_id":"2306.04293","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-need-holistically","slug":"large-language-models-need-holistically","title":"Large Language Models Need Holistically Thought in Medical Conversational QA","date":"2023-05-09","arxiv_id":"2305.05410","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/large-language-models-need-holistically#ran","syntology_url":"https://syntology.ai/paper/2305.05410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05410"}},"official":{"repos":["wengsyx/hot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/explainable-conversational-question-answering","slug":"explainable-conversational-question-answering","title":"Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks","date":"2023-05-02","arxiv_id":"2305.01548","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/semantic-parsing-for-conversational-question","slug":"semantic-parsing-for-conversational-question","title":"Semantic Parsing for Conversational Question Answering over Knowledge Graphs","date":"2023-01-28","arxiv_id":"2301.12217","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-conversational-question-answering","slug":"open-domain-conversational-question-answering","title":"Open-Domain Conversational Question Answering with Historical Answers","date":"2022-11-17","arxiv_id":"2211.09401","repositories_listed":1,"syntology":null},{"url":"/paper/pacific-towards-proactive-conversational","slug":"pacific-towards-proactive-conversational","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","date":"2022-10-17","arxiv_id":"2210.08817","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pacific-towards-proactive-conversational#ran","syntology_url":"https://syntology.ai/paper/2210.08817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08817"}},"official":{"repos":["dengyang17/pacific"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/contrastive-representation-learning-for-1","slug":"contrastive-representation-learning-for-1","title":"Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs","date":"2022-10-09","arxiv_id":"2210.04373","repositories_listed":1,"syntology":null},{"url":"/paper/convfinqa-exploring-the-chain-of-numerical","slug":"convfinqa-exploring-the-chain-of-numerical","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","date":"2022-10-07","arxiv_id":"2210.03849","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/convfinqa-exploring-the-chain-of-numerical#ran","syntology_url":"https://syntology.ai/paper/2210.03849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03849"}},"official":{"repos":["czyssrs/convfinqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/coqar-question-rewriting-on-coqa","slug":"coqar-question-rewriting-on-coqa","title":"CoQAR: Question Rewriting on CoQA","date":"2022-07-07","arxiv_id":"2207.03240","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-conversational-interaction-for","slug":"capturing-conversational-interaction-for","title":"Capturing Conversational Interaction for Question Answering via Global History Reasoning","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-dialogue-history","slug":"on-the-robustness-of-dialogue-history","title":"On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method","date":"2022-06-29","arxiv_id":"2206.14796","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","repositories_listed":1,"syntology":null},{"url":"/paper/dialog-inpainting-turning-documents-into","slug":"dialog-inpainting-turning-documents-into","title":"Dialog Inpainting: Turning Documents into Dialogs","date":"2022-05-18","arxiv_id":"2205.09073","repositories_listed":1,"syntology":null},{"url":"/paper/kafsp-knowledge-aware-fuzzy-semantic-parsing","slug":"kafsp-knowledge-aware-fuzzy-semantic-parsing","title":"KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mmcoqa-conversational-question-answering-over","slug":"mmcoqa-conversational-question-answering-over","title":"MMCoQA: Conversational Question Answering over Text, Tables, and Images","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lingyi-medical-conversational-question","slug":"lingyi-medical-conversational-question","title":"LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs","date":"2022-04-20","arxiv_id":"2204.09220","repositories_listed":1,"syntology":null},{"url":"/paper/can-question-rewriting-help-conversational","slug":"can-question-rewriting-help-conversational","title":"Can Question Rewriting Help Conversational Question Answering?","date":"2022-04-13","arxiv_id":"2204.06239","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-question-rewriting-help-conversational#ran","syntology_url":"https://syntology.ai/paper/2204.06239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06239"}},"official":{"repos":["hltchkust/cqr4cqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fedqas-privacy-aware-machine-reading","slug":"fedqas-privacy-aware-machine-reading","title":"FedQAS: Privacy-aware machine reading comprehension with federated learning","date":"2022-02-09","arxiv_id":"2202.04742","repositories_listed":1,"syntology":null},{"url":"/paper/scai-qrecc-shared-task-on-conversational","slug":"scai-qrecc-shared-task-on-conversational","title":"SCAI-QReCC Shared Task on Conversational Question Answering","date":"2022-01-26","arxiv_id":"2201.11094","repositories_listed":1,"syntology":null},{"url":"/paper/question-rewriting-assessing-its-importance","slug":"question-rewriting-assessing-its-importance","title":"Question rewriting? Assessing its importance for conversational question answering","date":"2022-01-22","arxiv_id":"2201.09146","repositories_listed":1,"syntology":null},{"url":"/paper/topiocqa-open-domain-conversational-question","slug":"topiocqa-open-domain-conversational-question","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","date":"2021-10-02","arxiv_id":"2110.00768","repositories_listed":1,"syntology":null},{"url":"/paper/abg-coqa-clarifying-ambiguity-in","slug":"abg-coqa-clarifying-ambiguity-in","title":"Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering","date":"2021-06-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learn-to-resolve-conversational-dependency-a","slug":"learn-to-resolve-conversational-dependency-a","title":"Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering","date":"2021-06-22","arxiv_id":"2106.11575","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learn-to-resolve-conversational-dependency-a#ran","syntology_url":"https://syntology.ai/paper/2106.11575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11575"}},"official":{"repos":["dmis-lab/excord"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-from-reformulations-in","slug":"reinforcement-learning-from-reformulations-in","title":"Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs","date":"2021-05-11","arxiv_id":"2105.04850","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-question-answering-over-1","slug":"conversational-question-answering-over-1","title":"Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks","date":"2021-04-04","arxiv_id":"2104.01569","repositories_listed":1,"syntology":null},{"url":"/paper/context-transformer-with-stacked-pointer","slug":"context-transformer-with-stacked-pointer","title":"Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs","date":"2021-03-13","arxiv_id":"2103.07766","repositories_listed":1,"syntology":null},{"url":"/paper/paraqa-a-question-answering-dataset-with","slug":"paraqa-a-question-answering-dataset-with","title":"ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation","date":"2021-03-13","arxiv_id":"2103.07771","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-open-retrieval","slug":"weakly-supervised-open-retrieval","title":"Weakly-Supervised Open-Retrieval Conversational Question Answering","date":"2021-03-03","arxiv_id":"2103.02537","repositories_listed":1,"syntology":null},{"url":"/paper/chaincqg-flow-aware-conversational-question","slug":"chaincqg-flow-aware-conversational-question","title":"ChainCQG: Flow-Aware Conversational Question Generation","date":"2021-02-04","arxiv_id":"2102.02864","repositories_listed":1,"syntology":null},{"url":"/paper/improving-conversational-question-answering","slug":"improving-conversational-question-answering","title":"Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning","date":"2020-11-01","arxiv_id":"2011.00615","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/open-retrieval-conversational-question","slug":"open-retrieval-conversational-question","title":"Open-Retrieval Conversational Question Answering","date":"2020-05-22","arxiv_id":"2005.11364","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-retrieval-conversational-question#ran","syntology_url":"https://syntology.ai/paper/2005.11364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11364"}},"official":{"repos":["prdwb/orconvqa-release"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/fluent-response-generation-for-conversational","slug":"fluent-response-generation-for-conversational","title":"Fluent Response Generation for Conversational Question Answering","date":"2020-05-21","arxiv_id":"2005.10464","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-question-answering-over","slug":"conversational-question-answering-over","title":"Conversational Question Answering over Passages by Leveraging Word Proximity Networks","date":"2020-04-27","arxiv_id":"2004.13117","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-for-conversational","slug":"multi-task-learning-for-conversational","title":"Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base","date":"2019-10-11","arxiv_id":"1910.05069","repositories_listed":1,"syntology":null},{"url":"/paper/look-before-you-hop-conversational-question","slug":"look-before-you-hop-conversational-question","title":"Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion","date":"2019-10-08","arxiv_id":"1910.03262","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/look-before-you-hop-conversational-question#ran","syntology_url":"https://syntology.ai/paper/1910.03262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.03262"}},"official":{"repos":["PhilippChr/CONVEX"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-content-understanding","slug":"an-empirical-study-of-content-understanding","title":"An Empirical Study of Content Understanding in Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10743","repositories_listed":1,"syntology":null},{"url":"/paper/bert-with-history-answer-embedding-for","slug":"bert-with-history-answer-embedding-for","title":"BERT with History Answer Embedding for Conversational Question Answering","date":"2019-05-14","arxiv_id":"1905.05412","repositories_listed":1,"syntology":null},{"url":"/paper/dialog-to-action-conversational-question","slug":"dialog-to-action-conversational-question","title":"Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-natural-language-understanding","slug":"evaluating-natural-language-understanding","title":"Evaluating Natural Language Understanding Services for Conversational Question Answering Systems","date":"2017-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"disambiguation-in-conversational-question","title":"Disambiguation in Conversational Question Answering in the Era of LLM: A Survey","date":"2025-05-18","arxiv_id":"2505.12543","repositories_listed":0,"syntology":null},{"url":null,"slug":"bottom-up-synthesis-of-knowledge-grounded","title":"Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts","date":"2025-04-19","arxiv_id":"2504.14375","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-factual-benchmarking-for-in-car","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","date":"2025-04-01","arxiv_id":"2504.01248","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-policy-de-composition-in","title":"Few-shot Policy (de)composition in Conversational Question Answering","date":"2025-01-20","arxiv_id":"2501.11335","repositories_listed":0,"syntology":null},{"url":null,"slug":"ragonite-iterative-retrieval-on-induced","title":"RAGONITE: Iterative Retrieval on Induced Databases and Verbalized RDF for Conversational QA over KGs with RAG","date":"2024-12-23","arxiv_id":"2412.17690","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidence-contextualization-and-counterfactual","title":"Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems","date":"2024-12-13","arxiv_id":"2412.10571","repositories_listed":0,"syntology":null},{"url":null,"slug":"qa-toolbox-conversational-question-answering","title":"QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturing","date":"2024-12-03","arxiv_id":"2412.02638","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcqpr-proactive-conversational-question","title":"PCQPR: Proactive Conversational Question Planning with Reflection","date":"2024-10-02","arxiv_id":"2410.01363","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-models-for-3","title":"Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents","date":"2024-10-01","arxiv_id":"2410.00526","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-when-to-retrieve-what-to-rewrite-and","title":"Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA","date":"2024-09-23","arxiv_id":"2409.15515","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-query-reformulation-with-the","title":"Conversational Query Reformulation with the Guidance of Retrieved Documents","date":"2024-07-17","arxiv_id":"2407.12363","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-query-rewriting-aligning-rewriters","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","date":"2024-06-16","arxiv_id":"2406.10991","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-large-language-models-with-graph","title":"Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering","date":"2024-06-14","arxiv_id":"2407.09506","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesizing-conversations-from-unlabeled","title":"Synthesizing Conversations from Unlabeled Documents using Automatic Response Segmentation","date":"2024-06-06","arxiv_id":"2406.03703","repositories_listed":0,"syntology":null},{"url":null,"slug":"conv-coa-improving-open-domain-question","title":"Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action","date":"2024-05-28","arxiv_id":"2405.17822","repositories_listed":0,"syntology":null},{"url":null,"slug":"perkwe-coqa-enhance-persian-conversational","title":"PerkwE_COQA: Enhanced Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models","date":"2024-04-08","arxiv_id":"2404.05406","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-conversational-question-answering","title":"Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check","date":"2024-03-27","arxiv_id":"2403.18243","repositories_listed":0,"syntology":null},{"url":null,"slug":"mp2d-an-automated-topic-shift-dialogue","title":"MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs","date":"2024-03-09","arxiv_id":"2403.05814","repositories_listed":0,"syntology":null},{"url":"/paper/chatqa-building-gpt-4-level-conversational-qa","slug":"chatqa-building-gpt-4-level-conversational-qa","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","date":"2024-01-18","arxiv_id":"2401.10225","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-conversational","title":"Reinforcement Learning for Conversational Question Answering over Knowledge Graph","date":"2024-01-16","arxiv_id":"2401.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-question-answering-with","title":"Conversational Question Answering with Reformulations over Knowledge Graph","date":"2023-12-27","arxiv_id":"2312.17269","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2m-converting-single-turn-to-multi-turn","title":"S2M: Converting Single-Turn to Multi-Turn Datasets for Conversational Question Answering","date":"2023-12-27","arxiv_id":"2312.16511","repositories_listed":0,"syntology":null},{"url":null,"slug":"inca-rethinking-in-car-conversational-system","title":"InCA: Rethinking In-Car Conversational System Assessment Leveraging Large Language Models","date":"2023-11-13","arxiv_id":"2311.07469","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogizer-context-aware-conversational-qa","title":"Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources","date":"2023-11-09","arxiv_id":"2311.07589","repositories_listed":0,"syntology":null},{"url":null,"slug":"ehrtutor-enhancing-patient-understanding-of","title":"EHRTutor: Enhancing Patient Understanding of Discharge Instructions","date":"2023-10-30","arxiv_id":"2310.19212","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-and-efficient-baselines-for-open","title":"Strong and Efficient Baselines for Open Domain Conversational Question Answering","date":"2023-10-23","arxiv_id":"2310.14708","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-training-for-conversational-question","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","date":"2023-10-20","arxiv_id":"2310.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"carexpert-leveraging-large-language-models","title":"CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering","date":"2023-10-14","arxiv_id":"2310.09536","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-guided-copy-mechanism-for","title":"Prompt Guided Copy Mechanism for Conversational Question Answering","date":"2023-08-07","arxiv_id":"2308.03422","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-select-the-relevant-history-turns","title":"Learning to Select the Relevant History Turns in Conversational Question Answering","date":"2023-08-04","arxiv_id":"2308.02294","repositories_listed":0,"syntology":null},{"url":null,"slug":"diplomat-a-dialogue-dataset-for-situated","title":"DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning","date":"2023-06-15","arxiv_id":"2306.09030","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dangers-of-trusting-stochastic-parrots","title":"The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering","date":"2023-05-25","arxiv_id":"2305.16519","repositories_listed":0,"syntology":null},{"url":null,"slug":"keeping-the-questions-conversational-using","title":"Keeping the Questions Conversational: Using Structured Representations to Resolve Dependency in Conversational Question Answering","date":"2023-04-14","arxiv_id":"2304.07125","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-leveraging-latent-knowledge-and","title":"Towards leveraging latent knowledge and Dialogue context for real-world conversational question answering","date":"2022-12-17","arxiv_id":"2212.08946","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-question-rewriting-for","title":"Reinforced Question Rewriting for Conversational Question Answering","date":"2022-10-27","arxiv_id":"2210.15777","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-type-conversational-question-answer","title":"Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions","date":"2022-10-24","arxiv_id":"2210.12979","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-3-lm-probabilistically-permuted-prophet","title":"P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training","date":"2022-10-22","arxiv_id":"2210.12339","repositories_listed":0,"syntology":null}],"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"},"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":10,"papers_where_code_ran_first_page":"/task/conversational-question-answering/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/conversational-question-answering/papers/2","json":"/task/conversational-question-answering/papers/2.json","rows":42},{"order":"ran","page":1,"of":1,"url":"/task/conversational-question-answering/papers/ran/1","json":"/task/conversational-question-answering/papers/ran/1.json","rows":10}],"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":"687da4e942eedcecb8e43747e9f19e7d8c0563860b86786aeee80286ade2fabb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}