{"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/task-oriented-dialogue-systems/papers/ran/1","list_of":"/task/task-oriented-dialogue-systems","task":"Task-Oriented Dialogue Systems","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,17],"of":17,"counts":{"archive_papers_tagged":308,"with_a_code_link":131,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":308,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":17,"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"},"first_page":"/task/task-oriented-dialogue-systems/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/meditod-an-english-dialogue-dataset-for","slug":"meditod-an-english-dialogue-dataset-for","title":"MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations","date":"2024-10-18","arxiv_id":"2410.14204","repositories_listed":0,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/meditod-an-english-dialogue-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2410.14204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14204"}},"official":null}},{"url":"/paper/confidence-estimation-for-llm-based-dialogue","slug":"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_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/confidence-estimation-for-llm-based-dialogue#ran","syntology_url":"https://syntology.ai/paper/2409.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09629"}},"official":{"repos":["jennycs0830/confidence_score_dst"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/duetsim-building-user-simulator-with-dual","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/duetsim-building-user-simulator-with-dual#ran","syntology_url":"https://syntology.ai/paper/2405.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13028"}},"official":{"repos":["suntea233/duetsim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fantastic-rewards-and-how-to-tame-them-a-case","slug":"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":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fantastic-rewards-and-how-to-tame-them-a-case#ran","syntology_url":"https://syntology.ai/paper/2302.10342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10342"}},"official":{"repos":["budzianowski/multiwoz","shentao-yang/fantastic_reward_iclr2023"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/textbox-2-0-a-text-generation-library-with","slug":"textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","arxiv_id":"2212.13005","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}},"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-zero-and-few-shot-generalization-in","slug":"improving-zero-and-few-shot-generalization-in","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","date":"2022-05-25","arxiv_id":"2205.12673","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/improving-zero-and-few-shot-generalization-in#ran","syntology_url":"https://syntology.ai/paper/2205.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12673"}},"official":{"repos":["prakharguptaz/Instructdial"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metaphorical-user-simulators-for-evaluating","slug":"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":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"7 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/metaphorical-user-simulators-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2204.00763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00763"}},"official":{"repos":["superbooming/simtester","sunnweiwei/metasim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unifiedskg-unifying-and-multi-tasking","slug":"unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","arxiv_id":"2201.05966","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/unifiedskg-unifying-and-multi-tasking#ran","syntology_url":"https://syntology.ai/paper/2201.05966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05966"}},"official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multiwoz-2-4-a-multi-domain-task-oriented","slug":"multiwoz-2-4-a-multi-domain-task-oriented","title":"MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation","date":"2021-04-01","arxiv_id":"2104.00773","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multiwoz-2-4-a-multi-domain-task-oriented#ran","syntology_url":"https://syntology.ai/paper/2104.00773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00773"}},"official":{"repos":["smartyfh/MultiWOZ2.4"],"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":["official","unlocated"]}}},{"url":"/paper/action-based-conversations-dataset-a-corpus","slug":"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":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/action-based-conversations-dataset-a-corpus#ran","syntology_url":"https://syntology.ai/paper/2104.00783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00783"}},"official":{"repos":["asappresearch/abcd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/slot-self-attentive-dialogue-state-tracking","slug":"slot-self-attentive-dialogue-state-tracking","title":"Slot Self-Attentive Dialogue State Tracking","date":"2021-01-22","arxiv_id":"2101.09374","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/slot-self-attentive-dialogue-state-tracking#ran","syntology_url":"https://syntology.ai/paper/2101.09374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.09374"}},"official":{"repos":["smartyfh/DST-STAR"],"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/mintl-minimalist-transfer-learning-for-task","slug":"mintl-minimalist-transfer-learning-for-task","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","date":"2020-09-25","arxiv_id":"2009.12005","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mintl-minimalist-transfer-learning-for-task#ran","syntology_url":"https://syntology.ai/paper/2009.12005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12005"}},"official":{"repos":["zlinao/MinTL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/convlab-2-an-open-source-toolkit-for-building","slug":"convlab-2-an-open-source-toolkit-for-building","title":"ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems","date":"2020-02-12","arxiv_id":"2002.04793","repositories_listed":1,"syntology":{"n":17,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/convlab-2-an-open-source-toolkit-for-building#ran","syntology_url":"https://syntology.ai/paper/2002.04793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04793"}},"official":{"repos":["thu-coai/ConvLab-2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/retrospective-and-prospective-mixture-of","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrospective-and-prospective-mixture-of#ran","syntology_url":"https://syntology.ai/paper/1911.08151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08151"}},"official":{"repos":["budzianowski/multiwoz","Jiahuan-Pei/multiwoz-mdrg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/global-to-local-memory-pointer-networks-for","slug":"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":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/global-to-local-memory-pointer-networks-for#ran","syntology_url":"https://syntology.ai/paper/1901.04713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.04713"}},"official":{"repos":["jasonwu0731/GLMP"],"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/global-locally-self-attentive-dialogue-state","slug":"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":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/global-locally-self-attentive-dialogue-state#ran","syntology_url":"https://syntology.ai/paper/1805.09655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09655"}},"official":{"repos":["salesforce/glad"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mem2seq-effectively-incorporating-knowledge","slug":"mem2seq-effectively-incorporating-knowledge","title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","date":"2018-04-23","arxiv_id":"1804.08217","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mem2seq-effectively-incorporating-knowledge#ran","syntology_url":"https://syntology.ai/paper/1804.08217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08217"}},"official":{"repos":["HLTCHKUST/Mem2Seq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}}],"record_sha256":"d9299af6e0be9ea7ed6688499ec1125674db393d3822cf7820d9d7727c38c913","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}