{"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 (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":63,"tagged_in_all":142,"items":[{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","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":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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","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","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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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}],"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"}}