{"url":"/task/response-generation","name":"Response Generation","slug":"response-generation","description_markdown":"A task where an agent should play the $DE$ role and generate a text to respond to a $P$ message.","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":914,"papers_with_code":370,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/response-generation-on-simmc2-0","slug":"response-generation-on-simmc2-0","dataset":"SIMMC2.0","dataset_url":"/dataset/simmc2-0","rows_in_archive":5,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/response-generation-on-argscichat","slug":"response-generation-on-argscichat","dataset":"ArgSciChat","dataset_url":"/dataset/argscichat","rows_in_archive":3,"metrics":["Message-F1","BScore","Mover"],"first_row_in_archive_order":{"model":"LED(Q,F)","paper_title":"ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers","paper_url":"/paper/argscichat-a-dataset-for-argumentative","paper_date":"2022-02-14","arxiv_id":"2202.06690","code_links":[{"title":"ukplab/arxiv2022-argscichat","url":"https://github.com/ukplab/arxiv2022-argscichat"},{"title":"federicoruggeri/argscichat_project","url":"https://github.com/federicoruggeri/argscichat_project"}],"syntology":null}},{"leaderboard":"/sota/response-generation-on-mmconv","slug":"response-generation-on-mmconv","dataset":"MMConv","dataset_url":"/dataset/mmconv","rows_in_archive":2,"metrics":["BLEU","Comb.","Inform","Success"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/prosocialdialog","name":"ProsocialDialog","full_name":"","num_papers_in_archive":13},{"url":"/dataset/simmc2-0","name":"SIMMC2.0","full_name":"","num_papers_in_archive":13},{"url":"/dataset/comfact","name":"ComFact","full_name":"","num_papers_in_archive":5},{"url":"/dataset/ketod","name":"KETOD","full_name":"Knowledge-Enriched Task-Oriented Dialogue","num_papers_in_archive":5},{"url":"/dataset/mmconv","name":"MMConv","full_name":"","num_papers_in_archive":3},{"url":"/dataset/argscichat","name":"ArgSciChat","full_name":"","num_papers_in_archive":1},{"url":"/dataset/comet","name":"Comet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":370,"tagged_in_all":914,"items":[{"url":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/a-diversity-promoting-objective-function-for","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","date":"2015-10-11","arxiv_id":"1510.03055","repositories_listed":14,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","repositories_listed":9,"syntology":null},{"url":"/paper/a-hierarchical-latent-variable-encoder","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","date":"2016-05-19","arxiv_id":"1605.06069","repositories_listed":9,"syntology":null},{"url":"/paper/nlg-evaluation-metrics-beyond-correlation","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","date":"2023-05-15","arxiv_id":"2305.08566","repositories_listed":7,"syntology":null},{"url":"/paper/mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","repositories_listed":7,"syntology":null},{"url":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","arxiv_id":"2310.11511","repositories_listed":6,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/dialogpt-large-scale-generative-pre-training","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","date":"2019-11-01","arxiv_id":"1911.00536","repositories_listed":6,"syntology":{"n":12,"n_ran":2,"n_unverified":10,"n_pointer_only":12}},{"url":"/paper/multiwoz-a-large-scale-multi-domain-wizard-of","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","date":"2018-09-29","arxiv_id":"1810.00278","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","arxiv_id":"2406.11280","repositories_listed":4,"syntology":{"n":30,"n_ran":20,"n_unverified":10,"n_pointer_only":15}},{"url":"/paper/towards-scalable-multi-domain-conversational","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","date":"2019-09-12","arxiv_id":"1909.05855","repositories_listed":4,"syntology":null},{"url":"/paper/multiresolution-recurrent-neural-networks-an","title":"Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation","date":"2016-06-02","arxiv_id":"1606.00776","repositories_listed":4,"syntology":null},{"url":"/paper/self-refine-iterative-refinement-with-self-1","title":"Self-Refine: Iterative Refinement with Self-Feedback","date":"2023-03-30","arxiv_id":"2303.17651","repositories_listed":3,"syntology":null},{"url":"/paper/plato-2-towards-building-an-open-domain","title":"PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning","date":"2020-06-30","arxiv_id":"2006.16779","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/cosql-a-conversational-text-to-sql-challenge","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","date":"2019-09-11","arxiv_id":"1909.05378","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/response-generation-by-context-aware","title":"Response Generation by Context-aware Prototype Editing","date":"2018-06-19","arxiv_id":"1806.07042","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/dialogwae-multimodal-response-generation-with","title":"DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder","date":"2018-05-31","arxiv_id":"1805.12352","repositories_listed":3,"syntology":null},{"url":"/paper/relevance-of-unsupervised-metrics-in-task","title":"Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation","date":"2017-06-29","arxiv_id":"1706.09799","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","repositories_listed":2,"syntology":null},{"url":"/paper/survey-on-abstractive-text-summarization","title":"Survey on Abstractive Text Summarization: Dataset, Models, and Metrics","date":"2024-12-22","arxiv_id":"2412.17165","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-multi-step-reasoning-abilities-of","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","date":"2024-10-11","arxiv_id":"2410.09302","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-explicit-reasoning-for-inference","title":"Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models","date":"2024-06-13","arxiv_id":"2406.09138","repositories_listed":2,"syntology":null},{"url":"/paper/uncovering-hidden-connections-iterative","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","date":"2023-10-11","arxiv_id":"2310.07259","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/compressing-context-to-enhance-inference","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","date":"2023-10-09","arxiv_id":"2310.06201","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/guiding-instruction-based-image-editing-via","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","date":"2023-09-29","arxiv_id":"2309.17102","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/controllable-generation-of-dialogue-acts-for","title":"Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking","date":"2023-07-26","arxiv_id":"2307.14440","repositories_listed":2,"syntology":null},{"url":"/paper/task-optimized-adapters-for-an-end-to-end","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","date":"2023-05-04","arxiv_id":"2305.02468","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"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/towards-a-unified-multi-dimensional-evaluator","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","date":"2022-10-13","arxiv_id":"2210.07197","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":14,"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"}}