{"url":"/task/task-oriented-dialogue-systems","name":"Task-Oriented Dialogue Systems","slug":"task-oriented-dialogue-systems","description_markdown":"Achieving a pre-defined task through a dialog.","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":308,"papers_with_code":131,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":22,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/task-oriented-dialogue-systems-on-kvret","slug":"task-oriented-dialogue-systems-on-kvret","dataset":"KVRET","dataset_url":null,"rows_in_archive":10,"metrics":["Entity F1","BLEU"],"first_row_in_archive_order":{"model":"T5-3b(UnifiedSKG)","paper_title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","paper_url":"/paper/unifiedskg-unifying-and-multi-tasking","paper_date":"2022-01-16","arxiv_id":"2201.05966","code_links":[{"title":"hkunlp/unifiedskg","url":"https://github.com/hkunlp/unifiedskg"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-sgd","slug":"task-oriented-dialogue-systems-on-sgd","dataset":"SGD","dataset_url":"/dataset/sgd","rows_in_archive":2,"metrics":["METEOR"],"first_row_in_archive_order":{"model":"T5","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","paper_url":"/paper/the-gem-benchmark-natural-language-generation","paper_date":"2021-02-02","arxiv_id":"2102.01672","code_links":[],"syntology":null}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-kvret-1","slug":"task-oriented-dialogue-systems-on-kvret-1","dataset":"Kvret","dataset_url":null,"rows_in_archive":1,"metrics":["Entity F1"],"first_row_in_archive_order":{"model":"DF-Net","paper_title":"Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog","paper_url":"/paper/dynamic-fusion-network-for-multi-domain-end","paper_date":"2020-04-23","arxiv_id":"2004.11019","code_links":[{"title":"LooperXX/DF-Net","url":"https://github.com/LooperXX/DF-Net"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/task-oriented-dialogue-systems-on-multiwoz-2","slug":"task-oriented-dialogue-systems-on-multiwoz-2","dataset":"MULTIWOZ 2.0","dataset_url":"/dataset/multiwoz","rows_in_archive":1,"metrics":["BLEU-4","Score"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/multiwoz","name":"MultiWOZ","full_name":"Multi-domain Wizard-of-Oz","num_papers_in_archive":328},{"url":"/dataset/sgd","name":"SGD","full_name":"Schema-Guided Dialogue","num_papers_in_archive":186},{"url":"/dataset/mutual","name":"MuTual","full_name":"MuTual","num_papers_in_archive":55},{"url":"/dataset/crosswoz","name":"CrossWOZ","full_name":"CrossWOZ","num_papers_in_archive":25},{"url":"/dataset/topv2","name":"TOPv2","full_name":"Task Oriented Parsing v2","num_papers_in_archive":25},{"url":"/dataset/abcd","name":"ABCD","full_name":"Action-Based Conversations Dataset","num_papers_in_archive":10},{"url":"/dataset/bitod","name":"BiToD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/a-game-of-sorts","name":"A Game Of Sorts","full_name":"","num_papers_in_archive":4},{"url":"/dataset/odsqa","name":"ODSQA","full_name":"Open-Domain Spoken Question Answering","num_papers_in_archive":3},{"url":"/dataset/task2dial","name":"Task2Dial","full_name":"","num_papers_in_archive":3},{"url":"/dataset/ssd-1","name":"SSD","full_name":"Sub-Slot Dialogue dataset","num_papers_in_archive":2},{"url":"/dataset/ssd-phone","name":"SSD_PHONE","full_name":"Sub-Slot Dialogue dataset phone domain","num_papers_in_archive":2},{"url":"/dataset/arabic-tod","name":"Arabic-ToD","full_name":"Arabic-ToD: Arabic Task Oriented Dialogue dataset","num_papers_in_archive":1},{"url":"/dataset/benyfits","name":"BeNYfits","full_name":"New York City Public Benefits Eligibility Dialog Agent Benchmark","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/hr-multiwoz","name":"HR-Multiwoz","full_name":"","num_papers_in_archive":1},{"url":"/dataset/incremental-dialog-dataset","name":"Incremental Dialog Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1},{"url":"/dataset/multiwoz-coref","name":"MultiWOZ-coref","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/ssd-id","name":"SSD_ID","full_name":"Sub-Slot Dialogue dataset id number domain","num_papers_in_archive":1},{"url":"/dataset/ssd-name","name":"SSD_NAME","full_name":"Sub-Slot Dialogue dataset name domain","num_papers_in_archive":1},{"url":"/dataset/ssd-plate","name":"SSD_PLATE","full_name":"Sub-Slot Dialogue dataset license plate number domain","num_papers_in_archive":1}],"subtasks":[{"url":"/task/sstod","name":"SSTOD"}],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"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":131,"tagged_in_all":308,"items":[{"url":"/paper/a-user-simulator-for-task-completion","title":"A User Simulator for Task-Completion Dialogues","date":"2016-12-17","arxiv_id":"1612.05688","repositories_listed":10,"syntology":null},{"url":"/paper/global-to-local-memory-pointer-networks-for","title":"Global-to-local Memory Pointer Networks for Task-Oriented Dialogue","date":"2019-01-15","arxiv_id":"1901.04713","repositories_listed":4,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/multiwoz-2-3-a-multi-domain-task-oriented","title":"MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation","date":"2020-10-12","arxiv_id":"2010.05594","repositories_listed":3,"syntology":null},{"url":"/paper/key-value-retrieval-networks-for-task","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","date":"2017-05-15","arxiv_id":"1705.05414","repositories_listed":3,"syntology":null},{"url":"/paper/dialight-lightweight-multilingual-development","title":"DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models","date":"2024-01-04","arxiv_id":"2401.02208","repositories_listed":2,"syntology":null},{"url":"/paper/in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","repositories_listed":2,"syntology":null},{"url":"/paper/fantastic-rewards-and-how-to-tame-them-a-case","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","date":"2023-02-20","arxiv_id":"2302.10342","repositories_listed":2,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/metaphorical-user-simulators-for-evaluating","title":"Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems","date":"2022-04-02","arxiv_id":"2204.00763","repositories_listed":2,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/dora-toward-policy-optimization-for-task","title":"DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context","date":"2021-07-07","arxiv_id":"2107.03286","repositories_listed":2,"syntology":null},{"url":"/paper/action-based-conversations-dataset-a-corpus","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","date":"2021-04-01","arxiv_id":"2104.00783","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/conversation-graph-data-augmentation-training","title":"Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management","date":"2020-10-29","arxiv_id":"2010.15411","repositories_listed":2,"syntology":null},{"url":"/paper/modelling-hierarchical-structure-between","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System","date":"2020-06-11","arxiv_id":"2006.06814","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-domain-apis-task-oriented","title":"Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access","date":"2020-06-05","arxiv_id":"2006.03533","repositories_listed":2,"syntology":null},{"url":"/paper/crosswoz-a-large-scale-chinese-cross-domain","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","date":"2020-02-27","arxiv_id":"2002.11893","repositories_listed":2,"syntology":null},{"url":"/paper/retrospective-and-prospective-mixture-of","title":"Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation","date":"2019-11-19","arxiv_id":"1911.08151","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/transferable-multi-domain-state-generator-for","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","date":"2019-05-21","arxiv_id":"1905.08743","repositories_listed":2,"syntology":null},{"url":"/paper/global-locally-self-attentive-dialogue-state","title":"Global-Locally Self-Attentive Dialogue State Tracker","date":"2018-05-19","arxiv_id":"1805.09655","repositories_listed":2,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":3}},{"url":"/paper/when-to-act-when-to-wait-modeling-structural","title":"WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue","date":"2025-06-02","arxiv_id":"2506.01881","repositories_listed":1,"syntology":null},{"url":"/paper/enstom-enhancing-dialogue-systems-with","title":"EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance","date":"2025-05-22","arxiv_id":"2505.16526","repositories_listed":1,"syntology":null},{"url":"/paper/lanid-llm-assisted-new-intent-discovery","title":"LANID: LLM-assisted New Intent Discovery","date":"2025-03-31","arxiv_id":"2503.23740","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-graph-structures-and-large","title":"Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues","date":"2025-01-21","arxiv_id":"2501.11977","repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-label-enhanced-prototypical","title":"Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery","date":"2024-10-26","arxiv_id":"2410.20219","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-estimation-for-llm-based-dialogue","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","date":"2024-09-15","arxiv_id":"2409.09629","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":12}},{"url":"/paper/unsupervised-mutual-learning-of-dialogue","title":"Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation","date":"2024-05-30","arxiv_id":"2405.19799","repositories_listed":1,"syntology":null},{"url":"/paper/duetsim-building-user-simulator-with-dual","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","date":"2024-05-16","arxiv_id":"2405.13028","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/the-power-of-the-noisy-channel-unsupervised","title":"Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel","date":"2024-04-23","arxiv_id":"2404.15219","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/rethinking-the-evaluation-of-dialogue-systems","title":"Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs","date":"2024-04-19","arxiv_id":"2404.12994","repositories_listed":1,"syntology":null},{"url":"/paper/context-does-matter-implications-for","title":"Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems","date":"2024-04-15","arxiv_id":"2404.09980","repositories_listed":1,"syntology":null},{"url":"/paper/jmultiwoz-a-large-scale-japanese-multi-domain","title":"JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset","date":"2024-03-26","arxiv_id":"2403.17319","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}