{"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/explanation-generation","name":"Explanation Generation","slug":"explanation-generation","description_markdown":null,"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":235,"papers_with_code":92,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":9,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/explanation-generation-on-whoops","slug":"explanation-generation-on-whoops","dataset":"WHOOPS!","dataset_url":"/dataset/whoops","rows_in_archive":7,"metrics":["Human (%)","Accuracy"],"first_row_in_archive_order":{"model":"Ground-truth Caption -> GPT3 (Oracle)","paper_title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","paper_url":"/paper/breaking-common-sense-whoops-a-vision-and","paper_date":"2023-03-13","arxiv_id":"2303.07274","code_links":[],"syntology":null}},{"leaderboard":"/sota/explanation-generation-on-clevr-x","slug":"explanation-generation-on-clevr-x","dataset":"CLEVR-X","dataset_url":"/dataset/clevr-x","rows_in_archive":2,"metrics":["B4","M","RL","C","Acc"],"first_row_in_archive_order":{"model":"PJ-X","paper_title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","paper_url":"/paper/clevr-x-a-visual-reasoning-dataset-for","paper_date":"2022-04-05","arxiv_id":"2204.02380","code_links":[{"title":"explainableml/clevr-x","url":"https://github.com/explainableml/clevr-x"}],"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clevr-x-a-visual-reasoning-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2204.02380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02380"}},"official":{"repos":["explainableml/clevr-x"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/explanation-generation-on-e-snli-ve","slug":"explanation-generation-on-e-snli-ve","dataset":"e-SNLI-VE","dataset_url":"/dataset/e-snli-ve","rows_in_archive":2,"metrics":["Human Explanation Rating"],"first_row_in_archive_order":{"model":"OFA-X","paper_title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","paper_url":"/paper/harnessing-the-power-of-multi-task","paper_date":"2022-12-08","arxiv_id":"2212.04231","code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/explanation-generation-on-vcr","slug":"explanation-generation-on-vcr","dataset":"VCR","dataset_url":"/dataset/vcr","rows_in_archive":2,"metrics":["Human Explanation Rating"],"first_row_in_archive_order":{"model":"OFA-X-MT","paper_title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","paper_url":"/paper/harnessing-the-power-of-multi-task","paper_date":"2022-12-08","arxiv_id":"2212.04231","code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/explanation-generation-on-vqa-x","slug":"explanation-generation-on-vqa-x","dataset":"VQA-X","dataset_url":null,"rows_in_archive":2,"metrics":["Human Explanation Rating"],"first_row_in_archive_order":{"model":"OFA-X","paper_title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","paper_url":"/paper/harnessing-the-power-of-multi-task","paper_date":"2022-12-08","arxiv_id":"2212.04231","code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}],"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/vcr","name":"VCR","full_name":"Visual Commonsense Reasoning","num_papers_in_archive":179},{"url":"/dataset/e-snli-ve","name":"e-SNLI-VE","full_name":"","num_papers_in_archive":16},{"url":"/dataset/whoops","name":"WHOOPS!","full_name":"","num_papers_in_archive":14},{"url":"/dataset/e-kar","name":"E-KAR","full_name":"Benchmark for Explainable Knowledge-intensive Analogical Reasoning","num_papers_in_archive":9},{"url":"/dataset/clevr-x","name":"CLEVR-X","full_name":"","num_papers_in_archive":5},{"url":"/dataset/e-redial","name":"E-ReDial","full_name":"Explainable Recommendation Dialogues","num_papers_in_archive":2},{"url":"/dataset/sume","name":"SuMe","full_name":"A Dataset Towards Summarizing Biomedical Mechanisms","num_papers_in_archive":2},{"url":"/dataset/expunations","name":"ExPUNations","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spanex","name":"SpanEX","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":3,"rows_per_page":100,"shown":100,"of":235,"of_with_code":92,"tagged_in_all":235,"counts":{"archive_papers_tagged":235,"with_a_code_link":92,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":235,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/using-stratified-sampling-to-improve-lime","slug":"using-stratified-sampling-to-improve-lime","title":"Using Stratified Sampling to Improve LIME Image Explanations","date":"2024-03-26","arxiv_id":"2403.17742","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-collaboration-framework-for","slug":"multi-agent-collaboration-framework-for","title":"MACRec: a Multi-Agent Collaboration Framework for Recommendation","date":"2024-02-23","arxiv_id":"2402.15235","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/multi-agent-collaboration-framework-for#ran","syntology_url":"https://syntology.ai/paper/2402.15235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15235"}},"official":{"repos":["wzf2000/macrec"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explaining-black-box-text-modules-in-natural","slug":"explaining-black-box-text-modules-in-natural","title":"Explaining black box text modules in natural language with language models","date":"2023-05-17","arxiv_id":"2305.09863","repositories_listed":2,"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":1,"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/explaining-black-box-text-modules-in-natural#ran","syntology_url":"https://syntology.ai/paper/2305.09863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09863"}},"official":{"repos":["csinva/imodelsX","microsoft/automated-explanations"],"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"]}}},{"url":"/paper/explaining-patterns-in-data-with-language","slug":"explaining-patterns-in-data-with-language","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","date":"2022-10-04","arxiv_id":"2210.01848","repositories_listed":2,"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/explaining-patterns-in-data-with-language#ran","syntology_url":"https://syntology.ai/paper/2210.01848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01848"}},"official":{"repos":["csinva/imodelsX"],"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"]}}},{"url":"/paper/te2rules-extracting-rule-lists-from-tree","slug":"te2rules-extracting-rule-lists-from-tree","title":"TE2Rules: Explaining Tree Ensembles using Rules","date":"2022-06-29","arxiv_id":"2206.14359","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-end-to-end-training-of-knowledge","slug":"scalable-end-to-end-training-of-knowledge","title":"AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations","date":"2021-08-26","arxiv_id":"2108.11656","repositories_listed":2,"syntology":null},{"url":"/paper/explainable-automated-fact-checking-for","slug":"explainable-automated-fact-checking-for","title":"Explainable Automated Fact-Checking for Public Health Claims","date":"2020-10-19","arxiv_id":"2010.09926","repositories_listed":2,"syntology":null},{"url":"/paper/realfactbench-a-benchmark-for-evaluating","slug":"realfactbench-a-benchmark-for-evaluating","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","date":"2025-06-14","arxiv_id":"2506.12538","repositories_listed":1,"syntology":null},{"url":"/paper/litex-a-linguistic-taxonomy-of-explanations","slug":"litex-a-linguistic-taxonomy-of-explanations","title":"LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference","date":"2025-05-28","arxiv_id":"2505.22848","repositories_listed":1,"syntology":null},{"url":"/paper/does-rationale-quality-matter-enhancing","slug":"does-rationale-quality-matter-enhancing","title":"Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation","date":"2025-05-26","arxiv_id":"2505.20014","repositories_listed":1,"syntology":null},{"url":"/paper/snape-pm-building-and-utilizing-dynamic","slug":"snape-pm-building-and-utilizing-dynamic","title":"SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation","date":"2025-05-19","arxiv_id":"2505.13053","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-vision-language-model-in-face","slug":"rethinking-vision-language-model-in-face","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector","date":"2025-03-26","arxiv_id":"2503.20188","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rethinking-vision-language-model-in-face#ran","syntology_url":"https://syntology.ai/paper/2503.20188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20188"}},"official":{"repos":["chelsea234/m2f2_det"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/target-augmented-shared-fusion-based","slug":"target-augmented-shared-fusion-based","title":"Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation","date":"2025-02-11","arxiv_id":"2502.07391","repositories_listed":1,"syntology":null},{"url":"/paper/self-rationalization-in-the-wild-a-large","slug":"self-rationalization-in-the-wild-a-large","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","date":"2025-02-07","arxiv_id":"2502.04797","repositories_listed":1,"syntology":null},{"url":"/paper/indmask-inductive-explanation-for","slug":"indmask-inductive-explanation-for","title":"IndMask: Inductive Explanation for Multivariate Time Series Black-Box Models","date":"2024-10-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/take-it-easy-label-adaptive-self","slug":"take-it-easy-label-adaptive-self","title":"Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation","date":"2024-10-05","arxiv_id":"2410.04002","repositories_listed":1,"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/take-it-easy-label-adaptive-self#ran","syntology_url":"https://syntology.ai/paper/2410.04002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04002"}},"official":{"repos":["jingyng/label-adaptive-self-rationalization"],"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/multimodal-coherent-explanation-generation-of","slug":"multimodal-coherent-explanation-generation-of","title":"Multimodal Coherent Explanation Generation of Robot Failures","date":"2024-10-01","arxiv_id":"2410.00659","repositories_listed":1,"syntology":null},{"url":"/paper/fmdllama-financial-misinformation-detection","slug":"fmdllama-financial-misinformation-detection","title":"FMDLlama: Financial Misinformation Detection based on Large Language Models","date":"2024-09-24","arxiv_id":"2409.16452","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-persuasion-towards-conversational","slug":"beyond-persuasion-towards-conversational","title":"Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations","date":"2024-09-22","arxiv_id":"2409.14399","repositories_listed":1,"syntology":null},{"url":"/paper/cross-refine-improving-natural-language","slug":"cross-refine-improving-natural-language","title":"Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem","date":"2024-09-11","arxiv_id":"2409.07123","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-refine-improving-natural-language#ran","syntology_url":"https://syntology.ai/paper/2409.07123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07123"}},"official":{"repos":["qiaw99/Cross-Refine"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-explanations-for-recommendation-with","slug":"aligning-explanations-for-recommendation-with","title":"Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information","date":"2024-07-18","arxiv_id":"2407.13274","repositories_listed":1,"syntology":null},{"url":"/paper/xedgeai-a-human-centered-industrial","slug":"xedgeai-a-human-centered-industrial","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","date":"2024-07-16","arxiv_id":"2407.11771","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xedgeai-a-human-centered-industrial#ran","syntology_url":"https://syntology.ai/paper/2407.11771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11771"}},"official":{"repos":["analytics-everywhere-lab/vqixai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-distillation-for-personalized","slug":"preference-distillation-for-personalized","title":"Preference Distillation for Personalized Generative Recommendation","date":"2024-07-06","arxiv_id":"2407.05033","repositories_listed":1,"syntology":null},{"url":"/paper/global-human-guided-counterfactual","slug":"global-human-guided-counterfactual","title":"Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning","date":"2024-06-19","arxiv_id":"2406.13869","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-transparency-of-machine-generated","slug":"evaluating-transparency-of-machine-generated","title":"Evaluating Evidence Attribution in Generated Fact Checking Explanations","date":"2024-06-18","arxiv_id":"2406.12645","repositories_listed":1,"syntology":null},{"url":"/paper/tox-bart-leveraging-toxicity-attributes-for","slug":"tox-bart-leveraging-toxicity-attributes-for","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","date":"2024-06-06","arxiv_id":"2406.03953","repositories_listed":1,"syntology":null},{"url":"/paper/tell-me-why-explainable-public-health-fact","slug":"tell-me-why-explainable-public-health-fact","title":"Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models","date":"2024-05-15","arxiv_id":"2405.09454","repositories_listed":1,"syntology":null},{"url":"/paper/do-vision-language-decoders-use-images-and","slug":"do-vision-language-decoders-use-images-and","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","date":"2024-04-29","arxiv_id":"2404.18624","repositories_listed":1,"syntology":null},{"url":"/paper/ru22fact-optimizing-evidence-for-multilingual","slug":"ru22fact-optimizing-evidence-for-multilingual","title":"RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict","date":"2024-03-25","arxiv_id":"2403.16662","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unified-multi-modal-personalization","slug":"towards-unified-multi-modal-personalization","title":"Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond","date":"2024-03-15","arxiv_id":"2403.10667","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-unified-multi-modal-personalization#ran","syntology_url":"https://syntology.ai/paper/2403.10667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10667"}},"official":{"repos":["weitianxin/UniMP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/t-tame-trainable-attention-mechanism-for","slug":"t-tame-trainable-attention-mechanism-for","title":"T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers","date":"2024-03-07","arxiv_id":"2403.04523","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-veracity-predictions-with-evidence","slug":"explaining-veracity-predictions-with-evidence","title":"Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach","date":"2024-02-09","arxiv_id":"2402.06443","repositories_listed":1,"syntology":null},{"url":"/paper/sentiment-enhanced-graph-based-sarcasm","slug":"sentiment-enhanced-graph-based-sarcasm","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","date":"2024-02-06","arxiv_id":"2402.03658","repositories_listed":1,"syntology":null},{"url":"/paper/mismatch-quest-visual-and-textual-feedback","slug":"mismatch-quest-visual-and-textual-feedback","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","date":"2023-12-05","arxiv_id":"2312.03766","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/mismatch-quest-visual-and-textual-feedback#ran","syntology_url":"https://syntology.ai/paper/2312.03766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03766"}},"official":{"repos":["mismatchquest/mismatchquest"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gnn2r-weakly-supervised-rationale-providing","slug":"gnn2r-weakly-supervised-rationale-providing","title":"GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs","date":"2023-12-04","arxiv_id":"2312.02317","repositories_listed":1,"syntology":null},{"url":"/paper/recexplainer-aligning-large-language-models","slug":"recexplainer-aligning-large-language-models","title":"RecExplainer: Aligning Large Language Models for Explaining Recommendation Models","date":"2023-11-18","arxiv_id":"2311.10947","repositories_listed":1,"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/recexplainer-aligning-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.10947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10947"}},"official":{"repos":["microsoft/recai"],"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"]}}},{"url":"/paper/xplainllm-a-qa-explanation-dataset-for","slug":"xplainllm-a-qa-explanation-dataset-for","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","date":"2023-11-15","arxiv_id":"2311.08614","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-evaluation-of-gpt-4v-on","slug":"a-comprehensive-evaluation-of-gpt-4v-on","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","date":"2023-11-13","arxiv_id":"2311.07536","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-interactions-between-text-spans","slug":"explaining-interactions-between-text-spans","title":"Explaining Interactions Between Text Spans","date":"2023-10-20","arxiv_id":"2310.13506","repositories_listed":1,"syntology":null},{"url":"/paper/ex-fever-a-dataset-for-multi-hop-explainable","slug":"ex-fever-a-dataset-for-multi-hop-explainable","title":"EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification","date":"2023-10-15","arxiv_id":"2310.09754","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/ex-fever-a-dataset-for-multi-hop-explainable#ran","syntology_url":"https://syntology.ai/paper/2310.09754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09754"}},"official":{"repos":["dependentsign/EX-FEVER"],"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"]}}},{"url":"/paper/vlis-unimodal-language-models-guide","slug":"vlis-unimodal-language-models-guide","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","date":"2023-10-15","arxiv_id":"2310.09767","repositories_listed":1,"syntology":null},{"url":"/paper/llm4vis-explainable-visualization","slug":"llm4vis-explainable-visualization","title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","date":"2023-10-11","arxiv_id":"2310.07652","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/llm4vis-explainable-visualization#ran","syntology_url":"https://syntology.ai/paper/2310.07652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07652"}},"official":{"repos":["demoleiwang/llm4vis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-self-reinforcement-for-improving","slug":"exploring-self-reinforcement-for-improving","title":"Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models","date":"2023-09-19","arxiv_id":"2309.10444","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exploring-self-reinforcement-for-improving#ran","syntology_url":"https://syntology.ai/paper/2309.10444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10444"}},"official":{"repos":["strong-ai-lab/explanation-generation"],"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/fin-fact-a-benchmark-dataset-for-multimodal","slug":"fin-fact-a-benchmark-dataset-for-multimodal","title":"Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation","date":"2023-09-15","arxiv_id":"2309.08793","repositories_listed":1,"syntology":null},{"url":"/paper/healthfc-a-dataset-of-health-claims-for","slug":"healthfc-a-dataset-of-health-claims-for","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","date":"2023-09-15","arxiv_id":"2309.08503","repositories_listed":1,"syntology":null},{"url":"/paper/reward-engineering-for-generating-semi","slug":"reward-engineering-for-generating-semi","title":"Reward Engineering for Generating Semi-structured Explanation","date":"2023-09-15","arxiv_id":"2309.08347","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-interpretable-cross-modal","slug":"a-survey-on-interpretable-cross-modal","title":"A Survey on Interpretable Cross-modal Reasoning","date":"2023-09-05","arxiv_id":"2309.01955","repositories_listed":1,"syntology":null},{"url":"/paper/llmrec-benchmarking-large-language-models-on","slug":"llmrec-benchmarking-large-language-models-on","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","date":"2023-08-23","arxiv_id":"2308.12241","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llmrec-benchmarking-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2308.12241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12241"}},"official":{"repos":["williamliujl/llmrec"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adapting-to-change-robust-counterfactual","slug":"adapting-to-change-robust-counterfactual","title":"Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes","date":"2023-08-04","arxiv_id":"2308.02353","repositories_listed":1,"syntology":null},{"url":"/paper/sustainable-transparency-in-recommender","slug":"sustainable-transparency-in-recommender","title":"Sustainable transparency in Recommender Systems: Bayesian Ranking of Images for Explainability","date":"2023-07-27","arxiv_id":"2308.01196","repositories_listed":1,"syntology":null},{"url":"/paper/multi-source-semantic-graph-based-multimodal","slug":"multi-source-semantic-graph-based-multimodal","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","date":"2023-06-29","arxiv_id":"2306.16650","repositories_listed":1,"syntology":null},{"url":"/paper/towards-explainable-conversational","slug":"towards-explainable-conversational","title":"Towards Explainable Conversational Recommender Systems","date":"2023-05-27","arxiv_id":"2305.18363","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-labels-empowering-human-with-natural","slug":"beyond-labels-empowering-human-with-natural","title":"Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture","date":"2023-05-22","arxiv_id":"2305.12710","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-evaluation-for-conversational","slug":"rethinking-the-evaluation-for-conversational","title":"Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models","date":"2023-05-22","arxiv_id":"2305.13112","repositories_listed":1,"syntology":{"n":17,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/rethinking-the-evaluation-for-conversational#ran","syntology_url":"https://syntology.ai/paper/2305.13112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13112"}},"official":{"repos":["rucaibox/ievalm-crs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/textual-explanations-for-automated-commentary","slug":"textual-explanations-for-automated-commentary","title":"Textual Explanations for Automated Commentary Driving","date":"2023-04-12","arxiv_id":"2304.08178","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-and-high-faithfulness","slug":"fine-grained-and-high-faithfulness","title":"Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations","date":"2023-03-16","arxiv_id":"2303.09171","repositories_listed":1,"syntology":null},{"url":"/paper/variational-causal-inference-network-for","slug":"variational-causal-inference-network-for","title":"Variational Causal Inference Network for Explanatory Visual Question Answering","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/explanation-regeneration-via-information","slug":"explanation-regeneration-via-information","title":"Explanation Regeneration via Information Bottleneck","date":"2022-12-19","arxiv_id":"2212.09603","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-the-power-of-multi-task","slug":"harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}},"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/codeexp-explanatory-code-document-generation","slug":"codeexp-explanatory-code-document-generation","title":"CodeExp: Explanatory Code Document Generation","date":"2022-11-25","arxiv_id":"2211.15395","repositories_listed":1,"syntology":null},{"url":"/paper/octet-object-aware-counterfactual","slug":"octet-object-aware-counterfactual","title":"OCTET: Object-aware Counterfactual Explanations","date":"2022-11-22","arxiv_id":"2211.12380","repositories_listed":1,"syntology":null},{"url":"/paper/cells-a-parallel-corpus-for-biomedical-lay","slug":"cells-a-parallel-corpus-for-biomedical-lay","title":"Retrieval augmentation of large language models for lay language generation","date":"2022-11-07","arxiv_id":"2211.03818","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/cells-a-parallel-corpus-for-biomedical-lay#ran","syntology_url":"https://syntology.ai/paper/2211.03818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03818"}},"official":{"repos":["linguisticanomalies/pls_retrieval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/expunations-augmenting-puns-with-keywords-and","slug":"expunations-augmenting-puns-with-keywords-and","title":"ExPUNations: Augmenting Puns with Keywords and Explanations","date":"2022-10-24","arxiv_id":"2210.13513","repositories_listed":1,"syntology":null},{"url":"/paper/analogy-generation-by-prompting-large","slug":"analogy-generation-by-prompting-large","title":"Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT","date":"2022-10-09","arxiv_id":"2210.04186","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-explanation-from-e","slug":"learning-to-generate-explanation-from-e","title":"Learning to Generate Explanation from e-Hospital Services for Medical Suggestion","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ucepic-unifying-aspect-planning-and-lexical","slug":"ucepic-unifying-aspect-planning-and-lexical","title":"UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation","date":"2022-09-28","arxiv_id":"2209.13885","repositories_listed":1,"syntology":null},{"url":"/paper/sim2word-explaining-similarity-with","slug":"sim2word-explaining-similarity-with","title":"Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual Explanations","date":"2022-09-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chunk-aware-alignment-and-lexical-constraint","slug":"chunk-aware-alignment-and-lexical-constraint","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","date":"2022-07-23","arxiv_id":"2207.11401","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-legal-case-matching-via-inverse","slug":"explainable-legal-case-matching-via-inverse","title":"Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction","date":"2022-07-09","arxiv_id":"2207.04182","repositories_listed":1,"syntology":null},{"url":"/paper/nn2rules-extracting-rule-list-from-neural","slug":"nn2rules-extracting-rule-list-from-neural","title":"NN2Rules: Extracting Rule List from Neural Networks","date":"2022-07-04","arxiv_id":"2207.12271","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-multimodal-fact-checking-and","slug":"end-to-end-multimodal-fact-checking-and","title":"End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models","date":"2022-05-25","arxiv_id":"2205.12487","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/end-to-end-multimodal-fact-checking-and#ran","syntology_url":"https://syntology.ai/paper/2205.12487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12487"}},"official":{"repos":["VT-NLP/Mocheg"],"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":["official"]}}},{"url":"/paper/structured-flexible-and-robust-benchmarking","slug":"structured-flexible-and-robust-benchmarking","title":"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks","date":"2022-05-11","arxiv_id":"2205.05718","repositories_listed":1,"syntology":null},{"url":"/paper/clevr-x-a-visual-reasoning-dataset-for","slug":"clevr-x-a-visual-reasoning-dataset-for","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","date":"2022-04-05","arxiv_id":"2204.02380","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clevr-x-a-visual-reasoning-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2204.02380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02380"}},"official":{"repos":["explainableml/clevr-x"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rex-reasoning-aware-and-grounded-explanation","slug":"rex-reasoning-aware-and-grounded-explanation","title":"REX: Reasoning-aware and Grounded Explanation","date":"2022-03-11","arxiv_id":"2203.06107","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"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 1 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","sample_list":"/paper/rex-reasoning-aware-and-grounded-explanation#ran","syntology_url":"https://syntology.ai/paper/2203.06107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06107"}},"official":{"repos":["szzexpoi/rex"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-high-quality-explanations-for","slug":"generating-high-quality-explanations-for","title":"Generating High-Quality Explanations for Navigation in Partially-Revealed Environments","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-explanations-for-models-of","slug":"counterfactual-explanations-for-models-of","title":"Counterfactual Explanations for Models of Code","date":"2021-11-10","arxiv_id":"2111.05711","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-explainable-phrasal","slug":"weakly-supervised-explainable-phrasal","title":"Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic","date":"2021-09-18","arxiv_id":"2109.08927","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/weakly-supervised-explainable-phrasal#ran","syntology_url":"https://syntology.ai/paper/2109.08927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08927"}},"official":{"repos":["manga-uofa/epr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/inducing-semantic-grouping-of-latent-concepts","slug":"inducing-semantic-grouping-of-latent-concepts","title":"A Framework for Learning Ante-hoc Explainable Models via Concepts","date":"2021-08-25","arxiv_id":"2108.11761","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/inducing-semantic-grouping-of-latent-concepts#ran","syntology_url":"https://syntology.ai/paper/2108.11761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11761"}},"official":{"repos":["anirbansarkar-cs/Ante-hoc_Explainability_Concepts"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-explain-reinforce-counterfactual","slug":"learn-explain-reinforce-counterfactual","title":"Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model","date":"2021-08-21","arxiv_id":"2108.09451","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-debugger-for-black-box-machine","slug":"explainable-debugger-for-black-box-machine","title":"Explainable Debugger for Black-box Machine Learning Models","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-information-retrieval-approach-to-building","slug":"an-information-retrieval-approach-to-building","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","date":"2021-06-17","arxiv_id":"2106.09775","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/an-information-retrieval-approach-to-building#ran","syntology_url":"https://syntology.ai/paper/2106.09775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09775"}},"official":{"repos":["mdmustafizurrahman/An-Information-Retrieval-Approach-to-Building-Datasets-for-Hate-Speech-Detection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-high-quality-explanations-for-1","slug":"generating-high-quality-explanations-for-1","title":"Generating High-Quality Explanations for Navigation in Partially-Revealed Environments","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zorro-valid-sparse-and-stable-explanations-in","slug":"zorro-valid-sparse-and-stable-explanations-in","title":"Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks","date":"2021-05-18","arxiv_id":"2105.08621","repositories_listed":1,"syntology":null},{"url":"/paper/faithfully-explainable-recommendation-via","slug":"faithfully-explainable-recommendation-via","title":"Faithfully Explainable Recommendation via Neural Logic Reasoning","date":"2021-04-16","arxiv_id":"2104.07869","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":2,"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/faithfully-explainable-recommendation-via#ran","syntology_url":"https://syntology.ai/paper/2104.07869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07869"}},"official":{"repos":["orcax/LOGER"],"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/explain-and-predict-and-then-predict-again","slug":"explain-and-predict-and-then-predict-again","title":"Explain and Predict, and then Predict Again","date":"2021-01-11","arxiv_id":"2101.04109","repositories_listed":1,"syntology":null},{"url":"/paper/lirex-augmenting-language-inference-with","slug":"lirex-augmenting-language-inference-with","title":"LIREx: Augmenting Language Inference with Relevant Explanation","date":"2020-12-16","arxiv_id":"2012.09157","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-agency-by-revealing-suboptimality","slug":"explainable-agency-by-revealing-suboptimality","title":"Explainable Agency by Revealing Suboptimality in Child-Robot Learning Scenarios","date":"2020-11-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-interpretable-natural-language","slug":"towards-interpretable-natural-language","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","date":"2020-10-24","arxiv_id":"2011.05268","repositories_listed":1,"syntology":{"n":14,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":12,"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) · 12 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/towards-interpretable-natural-language#ran","syntology_url":"https://syntology.ai/paper/2011.05268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.05268"}},"official":{"repos":["JamesHujy/ELV"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/elaborative-simplification-content-addition","slug":"elaborative-simplification-content-addition","title":"Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification","date":"2020-10-20","arxiv_id":"2010.10035","repositories_listed":1,"syntology":null},{"url":"/paper/leakage-adjusted-simulatability-can-models","slug":"leakage-adjusted-simulatability-can-models","title":"Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?","date":"2020-10-08","arxiv_id":"2010.04119","repositories_listed":1,"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/leakage-adjusted-simulatability-can-models#ran","syntology_url":"https://syntology.ai/paper/2010.04119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04119"}},"official":{"repos":["peterbhase/LAS-NL-Explanations"],"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"]}}},{"url":"/paper/qed-a-framework-and-dataset-for-explanations","slug":"qed-a-framework-and-dataset-for-explanations","title":"QED: A Framework and Dataset for Explanations in Question Answering","date":"2020-09-08","arxiv_id":"2009.06354","repositories_listed":1,"syntology":null},{"url":"/paper/red-dragon-ai-at-textgraphs-2019-shared-task-1","slug":"red-dragon-ai-at-textgraphs-2019-shared-task-1","title":"Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation","date":"2019-11-20","arxiv_id":"1911.08976","repositories_listed":1,"syntology":null},{"url":null,"slug":"hierarchical-interaction-summarization-and","title":"Hierarchical Interaction Summarization and Contrastive Prompting for Explainable Recommendations","date":"2025-07-08","arxiv_id":"2507.06044","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-is-agentic-definitions","title":"The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems","date":"2025-07-02","arxiv_id":"2507.02097","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-rag-driven-anomaly-detection-and","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","date":"2025-05-20","arxiv_id":"2505.13828","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-budget-friendly-model-agnostic","title":"Towards Budget-Friendly Model-Agnostic Explanation Generation for Large Language Models","date":"2025-05-18","arxiv_id":"2505.12509","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-skyline-explanations-for-graph","title":"Generating Skyline Explanations for Graph Neural Networks","date":"2025-05-12","arxiv_id":"2505.07635","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-llms-explanations-to-boost","title":"Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification","date":"2025-05-09","arxiv_id":"2505.05744","repositories_listed":0,"syntology":null},{"url":null,"slug":"chartqa-x-generating-explanations-for-charts","title":"ChartQA-X: Generating Explanations for Charts","date":"2025-04-17","arxiv_id":"2504.13275","repositories_listed":0,"syntology":null},{"url":null,"slug":"tathyanyaya-and-factlegalllama-advancing","title":"TathyaNyaya and FactLegalLlama: Advancing Factual Judgment Prediction and Explanation in the Indian Legal Context","date":"2025-04-07","arxiv_id":"2504.04737","repositories_listed":0,"syntology":null}],"syntology_records":26,"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":26,"papers_where_code_ran_first_page":"/task/explanation-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":3,"url":"/task/explanation-generation/papers/2","json":"/task/explanation-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/explanation-generation/papers/3","json":"/task/explanation-generation/papers/3.json","rows":35},{"order":"ran","page":1,"of":1,"url":"/task/explanation-generation/papers/ran/1","json":"/task/explanation-generation/papers/ran/1.json","rows":26}],"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":"ae68f277ccd066d0377f3f7f94e586e2ce73d24e1e997e5179709efc4f2d0a20","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}