{"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/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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":10,"rows_per_page":100,"shown":100,"of":914,"of_with_code":370,"tagged_in_all":914,"counts":{"archive_papers_tagged":914,"with_a_code_link":370,"where_syntology_ran_a_sample":88,"not_listed_spam_title":0,"listed":914,"listed_where_code_ran":88,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":69,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":69,"listed_every_run_a_failure_of_syntologys_instrument":19,"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"},"items":[{"url":"/paper/language-models-are-unsupervised-multitask","slug":"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","slug":"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":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-diversity-promoting-objective-function-for#ran","syntology_url":"https://syntology.ai/paper/1510.03055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1510.03055"}},"official":null}},{"url":"/paper/unified-language-model-pre-training-for","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-rag-learning-to-retrieve-generate-and#ran","syntology_url":"https://syntology.ai/paper/2310.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11511"}},"official":{"repos":["AkariAsai/self-rag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/dialogpt-large-scale-generative-pre-training","slug":"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":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"6 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dialogpt-large-scale-generative-pre-training#ran","syntology_url":"https://syntology.ai/paper/1911.00536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00536"}},"official":{"repos":["microsoft/DialoGPT"],"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/multiwoz-a-large-scale-multi-domain-wizard-of","slug":"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":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/multiwoz-a-large-scale-multi-domain-wizard-of#ran","syntology_url":"https://syntology.ai/paper/1810.00278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.00278"}},"official":null}},{"url":"/paper/i-srt-aligning-large-multimodal-models-for","slug":"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":26,"n_constructed":0,"n_ran_checked":12,"n_instrument":14,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":6,"n_pointer_only":15,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 2 violated, 6 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/i-srt-aligning-large-multimodal-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.11280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11280"}},"official":{"repos":["snumprlab/SRT","snumprlab/isr-dpo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-scalable-multi-domain-conversational","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":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":0,"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/cosql-a-conversational-text-to-sql-challenge#ran","syntology_url":"https://syntology.ai/paper/1909.05378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05378"}},"official":{"repos":["ryanzhumich/editsql"],"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/response-generation-by-context-aware","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/response-generation-by-context-aware#ran","syntology_url":"https://syntology.ai/paper/1806.07042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07042"}},"official":{"repos":["MarkWuNLP/ResponseEdit"],"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/dialogwae-multimodal-response-generation-with","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relevance-of-unsupervised-metrics-in-task#ran","syntology_url":"https://syntology.ai/paper/1706.09799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.09799"}},"official":{"repos":["Maluuba/nlg-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/relevance-isn-t-all-you-need-scaling-rag","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncovering-hidden-connections-iterative#ran","syntology_url":"https://syntology.ai/paper/2310.07259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07259"}},"official":{"repos":["hyu-zhang/itr","Hyu-Zhang/ISR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/compressing-context-to-enhance-inference","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compressing-context-to-enhance-inference#ran","syntology_url":"https://syntology.ai/paper/2310.06201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06201"}},"official":{"repos":["liyucheng09/selective_context"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/guiding-instruction-based-image-editing-via","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/guiding-instruction-based-image-editing-via#ran","syntology_url":"https://syntology.ai/paper/2309.17102","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17102"}},"official":{"repos":["apple/ml-mgie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-generation-of-dialogue-acts-for","slug":"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","slug":"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/task-optimized-adapters-for-an-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2305.02468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02468"}},"official":{"repos":["budzianowski/multiwoz","sogang-isds/TOATOD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"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/towards-a-unified-multi-dimensional-evaluator","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/towards-a-unified-multi-dimensional-evaluator#ran","syntology_url":"https://syntology.ai/paper/2210.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07197"}},"official":{"repos":["maszhongming/unieval"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/joint-generator-ranker-learning-for-natural","slug":"joint-generator-ranker-learning-for-natural","title":"Joint Generator-Ranker Learning for Natural Language Generation","date":"2022-06-28","arxiv_id":"2206.13974","repositories_listed":2,"syntology":null},{"url":"/paper/structure-extraction-in-task-oriented","slug":"structure-extraction-in-task-oriented","title":"Structure Extraction in Task-Oriented Dialogues with Slot Clustering","date":"2022-02-28","arxiv_id":"2203.00073","repositories_listed":2,"syntology":null},{"url":"/paper/argscichat-a-dataset-for-argumentative","slug":"argscichat-a-dataset-for-argumentative","title":"ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers","date":"2022-02-14","arxiv_id":"2202.06690","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-bot-prompt-based-learning-for","slug":"few-shot-bot-prompt-based-learning-for","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","date":"2021-10-15","arxiv_id":"2110.08118","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/few-shot-bot-prompt-based-learning-for#ran","syntology_url":"https://syntology.ai/paper/2110.08118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08118"}},"official":{"repos":["andreamad8/FSB","tunib-ai/parallelformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dialograph-incorporating-interpretable-1","slug":"dialograph-incorporating-interpretable-1","title":"DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues","date":"2021-06-02","arxiv_id":"2106.00920","repositories_listed":2,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/dialograph-incorporating-interpretable-1#ran","syntology_url":"https://syntology.ai/paper/2106.00920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00920"}},"official":{"repos":["rishabhjoshi/DialoGraph_ICLR21"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hierarchical-transformer-for-task-oriented","slug":"hierarchical-transformer-for-task-oriented","title":"Hierarchical Transformer for Task Oriented Dialog Systems","date":"2020-10-24","arxiv_id":"2011.08067","repositories_listed":2,"syntology":null},{"url":"/paper/decoding-methods-for-neural-narrative","slug":"decoding-methods-for-neural-narrative","title":"Decoding Methods for Neural Narrative Generation","date":"2020-10-14","arxiv_id":"2010.07375","repositories_listed":2,"syntology":null},{"url":"/paper/towards-topic-guided-conversational","slug":"towards-topic-guided-conversational","title":"Towards Topic-Guided Conversational Recommender System","date":"2020-10-08","arxiv_id":"2010.04125","repositories_listed":2,"syntology":null},{"url":"/paper/group-wise-contrastive-learning-for-neural","slug":"group-wise-contrastive-learning-for-neural","title":"Group-wise Contrastive Learning for Neural Dialogue Generation","date":"2020-09-16","arxiv_id":"2009.07543","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-domain-apis-task-oriented","slug":"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/situated-and-interactive-multimodal","slug":"situated-and-interactive-multimodal","title":"Situated and Interactive Multimodal Conversations","date":"2020-06-02","arxiv_id":"2006.01460","repositories_listed":2,"syntology":null},{"url":"/paper/palm-pre-training-an-autoencoding","slug":"palm-pre-training-an-autoencoding","title":"PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation","date":"2020-04-14","arxiv_id":"2004.07159","repositories_listed":2,"syntology":null},{"url":"/paper/variational-transformers-for-diverse-response","slug":"variational-transformers-for-diverse-response","title":"Variational Transformers for Diverse Response Generation","date":"2020-03-28","arxiv_id":"2003.12738","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/variational-transformers-for-diverse-response#ran","syntology_url":"https://syntology.ai/paper/2003.12738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.12738"}},"official":{"repos":["zlinao/Variational-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"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/caire-an-end-to-end-empathetic-chatbot","slug":"caire-an-end-to-end-empathetic-chatbot","title":"CAiRE: An Empathetic Neural Chatbot","date":"2019-07-28","arxiv_id":"1907.12108","repositories_listed":2,"syntology":null},{"url":"/paper/recosa-detecting-the-relevant-contexts-with","slug":"recosa-detecting-the-relevant-contexts-with","title":"ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation","date":"2019-07-09","arxiv_id":"1907.05339","repositories_listed":2,"syntology":null},{"url":"/paper/semantically-conditioned-dialog-response","slug":"semantically-conditioned-dialog-response","title":"Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention","date":"2019-05-30","arxiv_id":"1905.12866","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantically-conditioned-dialog-response#ran","syntology_url":"https://syntology.ai/paper/1905.12866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12866"}},"official":{"repos":["budzianowski/multiwoz","wenhuchen/HDSA-Dialog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/improving-neural-conversational-models-with","slug":"improving-neural-conversational-models-with","title":"Improving Neural Conversational Models with Entropy-Based Data Filtering","date":"2019-05-14","arxiv_id":"1905.05471","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"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 0 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","sample_list":"/paper/improving-neural-conversational-models-with#ran","syntology_url":"https://syntology.ai/paper/1905.05471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05471"}},"official":{"repos":["ricsinaruto/NeuralChatbots-DataFiltering","ricsinaruto/dialog-eval"],"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"]}}},{"url":"/paper/cyclical-annealing-schedule-a-simple-approach","slug":"cyclical-annealing-schedule-a-simple-approach","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","date":"2019-03-25","arxiv_id":"1903.10145","repositories_listed":2,"syntology":null},{"url":"/paper/improving-neural-response-diversity-with","slug":"improving-neural-response-diversity-with","title":"Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss","date":"2019-02-25","arxiv_id":"1902.09191","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-discrete-sentence-representation","slug":"unsupervised-discrete-sentence-representation","title":"Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation","date":"2018-04-22","arxiv_id":"1804.08069","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-discrete-sentence-representation#ran","syntology_url":"https://syntology.ai/paper/1804.08069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08069"}},"official":{"repos":["snakeztc/NeuralDialog-LAED"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/how-not-to-evaluate-your-dialogue-system-an","slug":"how-not-to-evaluate-your-dialogue-system-an","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","date":"2016-03-25","arxiv_id":"1603.08023","repositories_listed":2,"syntology":null},{"url":"/paper/from-what-to-respond-to-when-to-respond","slug":"from-what-to-respond-to-when-to-respond","title":"From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents","date":"2025-06-17","arxiv_id":"2506.14285","repositories_listed":1,"syntology":null},{"url":"/paper/ciir-liverag-2025-optimizing-multi-agent","slug":"ciir-liverag-2025-optimizing-multi-agent","title":"CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-Training","date":"2025-06-12","arxiv_id":"2506.10844","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-large-language-models-to-maintain","slug":"teaching-large-language-models-to-maintain","title":"Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.16483","repositories_listed":1,"syntology":null},{"url":"/paper/deliberation-on-priors-trustworthy-reasoning","slug":"deliberation-on-priors-trustworthy-reasoning","title":"Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs","date":"2025-05-21","arxiv_id":"2505.15210","repositories_listed":1,"syntology":{"n":14,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deliberation-on-priors-trustworthy-reasoning#ran","syntology_url":"https://syntology.ai/paper/2505.15210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15210"}},"official":{"repos":["reml-group/deliberation-on-priors"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/void-in-language-models","slug":"void-in-language-models","title":"Void in Language Models","date":"2025-05-20","arxiv_id":"2505.14467","repositories_listed":1,"syntology":null},{"url":"/paper/neuro-symbolic-query-compiler","slug":"neuro-symbolic-query-compiler","title":"Neuro-Symbolic Query Compiler","date":"2025-05-17","arxiv_id":"2505.11932","repositories_listed":1,"syntology":null},{"url":"/paper/personalizing-large-language-models-using","slug":"personalizing-large-language-models-using","title":"Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph","date":"2025-05-15","arxiv_id":"2505.09945","repositories_listed":1,"syntology":null},{"url":"/paper/antidote-a-unified-framework-for-mitigating","slug":"antidote-a-unified-framework-for-mitigating","title":"Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception","date":"2025-04-29","arxiv_id":"2504.20468","repositories_listed":1,"syntology":null},{"url":"/paper/auto-slurp-a-benchmark-dataset-for-evaluating","slug":"auto-slurp-a-benchmark-dataset-for-evaluating","title":"Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant","date":"2025-04-25","arxiv_id":"2504.18373","repositories_listed":1,"syntology":null},{"url":"/paper/mscrs-multi-modal-semantic-graph-prompt","slug":"mscrs-multi-modal-semantic-graph-prompt","title":"MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender Systems","date":"2025-04-15","arxiv_id":"2504.10921","repositories_listed":1,"syntology":null},{"url":"/paper/safechat-a-framework-for-building-trustworthy","slug":"safechat-a-framework-for-building-trustworthy","title":"SafeChat: A Framework for Building Trustworthy Collaborative Assistants and a Case Study of its Usefulness","date":"2025-04-08","arxiv_id":"2504.07995","repositories_listed":1,"syntology":null},{"url":"/paper/agitb-a-signal-level-benchmark-for-evaluating","slug":"agitb-a-signal-level-benchmark-for-evaluating","title":"AGITB: A Signal-Level Benchmark for Evaluating Artificial General Intelligence","date":"2025-04-06","arxiv_id":"2504.04430","repositories_listed":1,"syntology":null},{"url":"/paper/comac-conversational-agent-for-multi-source","slug":"comac-conversational-agent-for-multi-source","title":"CoMAC: Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions","date":"2025-03-25","arxiv_id":"2503.19274","repositories_listed":1,"syntology":null},{"url":"/paper/ginger-grounded-information-nugget-based","slug":"ginger-grounded-information-nugget-based","title":"GINGER: Grounded Information Nugget-Based Generation of Responses","date":"2025-03-23","arxiv_id":"2503.18174","repositories_listed":1,"syntology":null},{"url":"/paper/fg-rag-enhancing-query-focused-summarization","slug":"fg-rag-enhancing-query-focused-summarization","title":"FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG","date":"2025-03-13","arxiv_id":"2504.07103","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-reasoning-queries-a-systematic","slug":"attentive-reasoning-queries-a-systematic","title":"Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models","date":"2025-03-05","arxiv_id":"2503.03669","repositories_listed":1,"syntology":null},{"url":"/paper/lexrag-benchmarking-retrieval-augmented","slug":"lexrag-benchmarking-retrieval-augmented","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","date":"2025-02-28","arxiv_id":"2502.20640","repositories_listed":1,"syntology":null},{"url":"/paper/pscon-toward-conversational-product-search","slug":"pscon-toward-conversational-product-search","title":"PSCon: Product Search Through Conversations","date":"2025-02-19","arxiv_id":"2502.13881","repositories_listed":1,"syntology":null},{"url":"/paper/grammar-control-in-dialogue-response","slug":"grammar-control-in-dialogue-response","title":"Grammar Control in Dialogue Response Generation for Language Learning Chatbots","date":"2025-02-11","arxiv_id":"2502.07544","repositories_listed":1,"syntology":null},{"url":"/paper/self-correcting-decoding-with-generative","slug":"self-correcting-decoding-with-generative","title":"Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models","date":"2025-02-10","arxiv_id":"2502.06130","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/self-correcting-decoding-with-generative#ran","syntology_url":"https://syntology.ai/paper/2502.06130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06130"}},"official":{"repos":["zhangce01/degf"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/a-video-grounded-dialogue-dataset-and-metric","slug":"a-video-grounded-dialogue-dataset-and-metric","title":"A Video-grounded Dialogue Dataset and Metric for Event-driven Activities","date":"2025-01-30","arxiv_id":"2501.18324","repositories_listed":1,"syntology":null},{"url":"/paper/agent4edu-generating-learner-response-data-by","slug":"agent4edu-generating-learner-response-data-by","title":"Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems","date":"2025-01-17","arxiv_id":"2501.10332","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent4edu-generating-learner-response-data-by#ran","syntology_url":"https://syntology.ai/paper/2501.10332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.10332"}},"official":{"repos":["bigdata-ustc/agent4edu"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bok-introducing-bag-of-keywords-loss-for","slug":"bok-introducing-bag-of-keywords-loss-for","title":"BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation","date":"2025-01-17","arxiv_id":"2501.10328","repositories_listed":1,"syntology":null},{"url":"/paper/videorag-retrieval-augmented-generation-over","slug":"videorag-retrieval-augmented-generation-over","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","date":"2025-01-10","arxiv_id":"2501.05874","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videorag-retrieval-augmented-generation-over#ran","syntology_url":"https://syntology.ai/paper/2501.05874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05874"}},"official":{"repos":["starsuzi/videorag"],"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"]}}},{"url":"/paper/mitigating-object-hallucinations-in-large-2","slug":"mitigating-object-hallucinations-in-large-2","title":"Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unified-understanding-of-environment-task-and","slug":"unified-understanding-of-environment-task-and","title":"Unified Understanding of Environment, Task, and Human for Human-Robot Interaction in Real-World Environments","date":"2024-12-18","arxiv_id":"2412.13726","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-llm-for-generating-customized","slug":"personalized-llm-for-generating-customized","title":"Personalized LLM for Generating Customized Responses to the Same Query from Different Users","date":"2024-12-16","arxiv_id":"2412.11736","repositories_listed":1,"syntology":null},{"url":"/paper/tool-ed-enhancing-empathetic-response","slug":"tool-ed-enhancing-empathetic-response","title":"TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM","date":"2024-12-04","arxiv_id":"2412.03096","repositories_listed":1,"syntology":null},{"url":"/paper/safe-safe-unsafe-exploring-how-safe-images","slug":"safe-safe-unsafe-exploring-how-safe-images","title":"Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models","date":"2024-11-18","arxiv_id":"2411.11496","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":1,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-safe-unsafe-exploring-how-safe-images#ran","syntology_url":"https://syntology.ai/paper/2411.11496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11496"}},"official":{"repos":["gzcch/safety_snowball_agent"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/coral-benchmarking-multi-turn-conversational","slug":"coral-benchmarking-multi-turn-conversational","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","date":"2024-10-30","arxiv_id":"2410.23090","repositories_listed":1,"syntology":null},{"url":"/paper/emotional-rag-enhancing-role-playing-agents","slug":"emotional-rag-enhancing-role-playing-agents","title":"Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval","date":"2024-10-30","arxiv_id":"2410.23041","repositories_listed":1,"syntology":null},{"url":"/paper/can-users-detect-biases-or-factual-errors-in","slug":"can-users-detect-biases-or-factual-errors-in","title":"Can Users Detect Biases or Factual Errors in Generated Responses in Conversational Information-Seeking?","date":"2024-10-28","arxiv_id":"2410.21529","repositories_listed":1,"syntology":null},{"url":"/paper/developing-retrieval-augmented-generation-rag","slug":"developing-retrieval-augmented-generation-rag","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","date":"2024-10-21","arxiv_id":"2410.15944","repositories_listed":1,"syntology":null},{"url":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","repositories_listed":1,"syntology":null},{"url":"/paper/self-adaptive-multimodal-retrieval-augmented","slug":"self-adaptive-multimodal-retrieval-augmented","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11321","repositories_listed":1,"syntology":null},{"url":"/paper/bio-eng-lmm-ai-assist-chatbot-a-comprehensive","slug":"bio-eng-lmm-ai-assist-chatbot-a-comprehensive","title":"Bio-Eng-LMM AI Assist chatbot: A Comprehensive Tool for Research and Education","date":"2024-09-11","arxiv_id":"2409.07110","repositories_listed":1,"syntology":null},{"url":"/paper/maferw-query-rewriting-with-multi-aspect","slug":"maferw-query-rewriting-with-multi-aspect","title":"MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models","date":"2024-08-30","arxiv_id":"2408.17072","repositories_listed":1,"syntology":null},{"url":"/paper/towards-empathetic-conversational-recommender","slug":"towards-empathetic-conversational-recommender","title":"Towards Empathetic Conversational Recommender Systems","date":"2024-08-30","arxiv_id":"2409.10527","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/towards-empathetic-conversational-recommender#ran","syntology_url":"https://syntology.ai/paper/2409.10527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10527"}},"official":{"repos":["zxd-octopus/ECR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/preference-guided-reflective-sampling-for","slug":"preference-guided-reflective-sampling-for","title":"Preference-Guided Reflective Sampling for Aligning Language Models","date":"2024-08-22","arxiv_id":"2408.12163","repositories_listed":1,"syntology":null},{"url":"/paper/lbc-language-based-classifier-for-out-of","slug":"lbc-language-based-classifier-for-out-of","title":"LBC: Language-Based-Classifier for Out-Of-Variable Generalization","date":"2024-08-20","arxiv_id":"2408.10923","repositories_listed":1,"syntology":null},{"url":"/paper/the-fellowship-of-the-llms-multi-agent","slug":"the-fellowship-of-the-llms-multi-agent","title":"The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation","date":"2024-08-16","arxiv_id":"2408.08688","repositories_listed":1,"syntology":null},{"url":"/paper/bi-mdrg-bridging-image-history-in-multimodal","slug":"bi-mdrg-bridging-image-history-in-multimodal","title":"BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation","date":"2024-08-12","arxiv_id":"2408.05926","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bi-mdrg-bridging-image-history-in-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.05926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05926"}},"official":{"repos":["hee-suk-yoon/bi-mdrg"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/medical-graph-rag-towards-safe-medical-large","slug":"medical-graph-rag-towards-safe-medical-large","title":"Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation","date":"2024-08-08","arxiv_id":"2408.04187","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/medical-graph-rag-towards-safe-medical-large#ran","syntology_url":"https://syntology.ai/paper/2408.04187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04187"}},"official":{"repos":["medicinetoken/medical-graph-rag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02976","slug":"2408-02976","title":"Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation","date":"2024-08-06","arxiv_id":"2408.02976","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03010","slug":"2408-03010","title":"Fact Finder -- Enhancing Domain Expertise of Large Language Models by Incorporating Knowledge Graphs","date":"2024-08-06","arxiv_id":"2408.03010","repositories_listed":1,"syntology":null},{"url":"/paper/from-feature-importance-to-natural-language","slug":"from-feature-importance-to-natural-language","title":"From Feature Importance to Natural Language Explanations Using LLMs with RAG","date":"2024-07-30","arxiv_id":"2407.20990","repositories_listed":1,"syntology":null},{"url":"/paper/towards-aligning-language-models-with-textual","slug":"towards-aligning-language-models-with-textual","title":"Towards Aligning Language Models with Textual Feedback","date":"2024-07-24","arxiv_id":"2407.16970","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/towards-aligning-language-models-with-textual#ran","syntology_url":"https://syntology.ai/paper/2407.16970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16970"}},"official":{"repos":["sauc-abadal/alt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/aptness-incorporating-appraisal-theory-and","slug":"aptness-incorporating-appraisal-theory-and","title":"APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation","date":"2024-07-23","arxiv_id":"2407.21048","repositories_listed":1,"syntology":null}],"syntology_records":30,"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"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":88,"papers_where_code_ran_first_page":"/task/response-generation/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":10,"url":"/task/response-generation/papers/2","json":"/task/response-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/response-generation/papers/3","json":"/task/response-generation/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/response-generation/papers/4","json":"/task/response-generation/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/response-generation/papers/5","json":"/task/response-generation/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/response-generation/papers/6","json":"/task/response-generation/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/response-generation/papers/7","json":"/task/response-generation/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/response-generation/papers/8","json":"/task/response-generation/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/response-generation/papers/9","json":"/task/response-generation/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/response-generation/papers/10","json":"/task/response-generation/papers/10.json","rows":14},{"order":"ran","page":1,"of":1,"url":"/task/response-generation/papers/ran/1","json":"/task/response-generation/papers/ran/1.json","rows":88}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"99b952f813803b8910f5ff03a54882b11d14e6fc38b3752b2c0d1104886b5cc6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}