{"url":"/task/interactive-evaluation-of-dialog","name":"Interactive Evaluation of Dialog","slug":"interactive-evaluation-of-dialog","description_markdown":"Task that involve building/adapting conversation models to work effectively in an interactive setting.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":4,"papers_with_code":2,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/interactive-evaluation-of-dialog-on-dstc9","slug":"interactive-evaluation-of-dialog-on-dstc9","dataset":"DSTC9 Track 3 - Task 2","dataset_url":null,"rows_in_archive":1,"metrics":["Overall Human Rating","Coherent","Error Recovery","Consistent","Diversity","Topic Depth","Likeable","Understanding","Flexible","Informative","Inquisitive"],"first_row_in_archive_order":{"model":"PLATO-2","paper_title":"A Unified Pre-training Framework for Conversational AI","paper_url":"/paper/a-unified-pre-training-framework-for","paper_date":"2021-05-06","arxiv_id":"2105.02482","code_links":[{"title":"PaddlePaddle/Knover","url":"https://github.com/PaddlePaddle/Knover"}],"syntology":null}}],"datasets":[],"subtasks":[],"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":2,"of":2,"tagged_in_all":4,"items":[{"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/a-unified-pre-training-framework-for","title":"A Unified Pre-training Framework for Conversational AI","date":"2021-05-06","arxiv_id":"2105.02482","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"}}