{"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":0,"n_unverified":8,"n_pointer_only":0}}},{"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":1,"n_unverified":7,"n_pointer_only":0}}},{"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":1,"n_unverified":7,"n_pointer_only":0}}},{"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":1,"n_unverified":7,"n_pointer_only":0}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":92,"tagged_in_all":235,"items":[{"url":"/paper/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","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_unverified":0,"n_pointer_only":3}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":4}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":11}},{"url":"/paper/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","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","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","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","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","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","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","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_unverified":1,"n_pointer_only":9}}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}