{"url":"/task/explainable-artificial-intelligence","name":"Explainable artificial intelligence","slug":"explainable-artificial-intelligence","description_markdown":"XAI refers to methods and techniques in the application of artificial intelligence (AI) such that the results of the solution can be understood by humans. It contrasts with the concept of the \"black box\" in machine learning where even its designers cannot explain why an AI arrived at a specific decision. XAI may be an implementation of the social right to explanation. XAI is relevant even if there is no legal right or regulatory requirement—for example, XAI can improve the user experience of a product or service by helping end users trust that the AI is making good decisions. This way the aim of XAI is to explain what has been done, what is done right now, what will be done next and unveil the information the actions are based on. These characteristics make it possible (i) to confirm existing knowledge (ii) to challenge existing knowledge and (iii) to generate new assumptions.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":971,"papers_with_code":305,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":3,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/bdd-x","name":"BDD-X","full_name":"Berkeley Deep Drive-X (eXplanation)","num_papers_in_archive":47},{"url":"/dataset/openxai","name":"OpenXAI","full_name":"","num_papers_in_archive":17},{"url":"/dataset/e-snli-ve","name":"e-SNLI-VE","full_name":"","num_papers_in_archive":16},{"url":"/dataset/e-vil","name":"e-ViL","full_name":"","num_papers_in_archive":10},{"url":"/dataset/xai-bench","name":"XAI-Bench","full_name":"","num_papers_in_archive":8},{"url":"/dataset/anthroprotect","name":"AnthroProtect","full_name":"","num_papers_in_archive":3},{"url":"/dataset/euca-dataset","name":"EUCA dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/exban","name":"ExBAN","full_name":"ExBAN Corpus (Explanations for BAyesian Networks)","num_papers_in_archive":1}],"subtasks":[{"url":"/task/explainable-models","name":"Explainable Models"},{"url":"/task/explanation-fidelity-evaluation","name":"Explanation Fidelity Evaluation"},{"url":"/task/fad-curve-analysis","name":"FAD Curve Analysis"}],"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":305,"tagged_in_all":971,"items":[{"url":"/paper/axiomatic-attribution-for-deep-networks","title":"Axiomatic Attribution for Deep Networks","date":"2017-03-04","arxiv_id":"1703.01365","repositories_listed":40,"syntology":{"n":56,"n_ran":36,"n_unverified":20,"n_pointer_only":17}},{"url":"/paper/gnn-explainer-a-tool-for-post-hoc-explanation","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","date":"2019-03-10","arxiv_id":"1903.03894","repositories_listed":12,"syntology":{"n":22,"n_ran":1,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/guidelines-for-responsible-and-human-centered","title":"Proposed Guidelines for the Responsible Use of Explainable Machine Learning","date":"2019-06-08","arxiv_id":"1906.03533","repositories_listed":5,"syntology":null},{"url":"/paper/software-for-dataset-wide-xai-from-local","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","date":"2021-06-24","arxiv_id":"2106.13200","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/megan-multi-explanation-graph-attention","title":"MEGAN: Multi-Explanation Graph Attention Network","date":"2022-11-23","arxiv_id":"2211.13236","repositories_listed":3,"syntology":null},{"url":"/paper/global-explanation-of-tree-ensembles-models","title":"Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective","date":"2022-10-18","arxiv_id":"2210.09933","repositories_listed":3,"syntology":null},{"url":"/paper/entropy-based-logic-explanations-of-neural","title":"Entropy-based Logic Explanations of Neural Networks","date":"2021-06-12","arxiv_id":"2106.06804","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/interpreting-and-explaining-deep-neural","title":"AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark","date":"2018-07-09","arxiv_id":"1807.03418","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/gcpv-guided-concept-projection-vectors-for","title":"Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces","date":"2023-11-24","arxiv_id":"2311.14435","repositories_listed":2,"syntology":null},{"url":"/paper/funnybirds-a-synthetic-vision-dataset-for-a","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","date":"2023-08-11","arxiv_id":"2308.06248","repositories_listed":2,"syntology":{"n":13,"n_ran":5,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/the-effect-of-balancing-methods-on-model","title":"The Effect of Balancing Methods on Model Behavior in Imbalanced Classification Problems","date":"2023-06-30","arxiv_id":"2307.00157","repositories_listed":2,"syntology":null},{"url":"/paper/black-box-model-explanations-and-the-human","title":"Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction","date":"2022-10-19","arxiv_id":"2210.10849","repositories_listed":2,"syntology":null},{"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/from-where-to-what-towards-human","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","date":"2022-06-07","arxiv_id":"2206.03208","repositories_listed":2,"syntology":null},{"url":"/paper/gam-e-changer-or-not-an-evaluation-of","title":"GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraints","date":"2022-04-19","arxiv_id":"2204.09123","repositories_listed":2,"syntology":null},{"url":"/paper/augmentative-explanation-and-the","title":"Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AI","date":"2021-12-30","arxiv_id":"2201.00009","repositories_listed":2,"syntology":null},{"url":"/paper/counterfactual-shapley-additive-explanations","title":"Counterfactual Shapley Additive Explanations","date":"2021-10-27","arxiv_id":"2110.14270","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/explaining-deep-learning-models-for-spoofing","title":"Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations","date":"2021-10-07","arxiv_id":"2110.03309","repositories_listed":2,"syntology":null},{"url":"/paper/logic-explained-networks","title":"Logic Explained Networks","date":"2021-08-11","arxiv_id":"2108.05149","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/quantitative-evaluation-of-explainable-graph","title":"Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction","date":"2021-07-01","arxiv_id":"2107.04119","repositories_listed":2,"syntology":null},{"url":"/paper/towards-rigorous-interpretations-a","title":"Towards Rigorous Interpretations: a Formalisation of Feature Attribution","date":"2021-04-26","arxiv_id":"2104.12437","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/quantifying-explainability-of-saliency","title":"Quantifying Explainability of Saliency Methods in Deep Neural Networks with a Synthetic Dataset","date":"2020-09-07","arxiv_id":"2009.02899","repositories_listed":2,"syntology":null},{"url":"/paper/explaining-how-deep-neural-networks-forget-by","title":"Explaining How Deep Neural Networks Forget by Deep Visualization","date":"2020-05-03","arxiv_id":"2005.01004","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/on-the-understanding-and-interpretation-of","title":"On the Explanation of Machine Learning Predictions in Clinical Gait Analysis","date":"2019-12-16","arxiv_id":"1912.07737","repositories_listed":2,"syntology":null},{"url":"/paper/ibreakdown-uncertainty-of-model-explanations","title":"Do Not Trust Additive Explanations","date":"2019-03-27","arxiv_id":"1903.11420","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/sopa-bridging-cnns-rnns-and-weighted-finite","title":"SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines","date":"2018-05-15","arxiv_id":"1805.06061","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/communicating-smartly-in-the-molecular-domain","title":"Communicating Smartly in the Molecular Domain: Neural Networks in the Internet of Bio-Nano Things","date":"2025-06-25","arxiv_id":"2506.20589","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08338","title":"midr: Learning from Black-Box Models by Maximum Interpretation Decomposition","date":"2025-06-10","arxiv_id":"2506.08338","repositories_listed":1,"syntology":null},{"url":"/paper/do-protein-transformers-have-biological","title":"Do Protein Transformers Have Biological Intelligence?","date":"2025-06-07","arxiv_id":"2506.06701","repositories_listed":1,"syntology":null},{"url":"/paper/timing-temporality-aware-integrated-gradients","title":"TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation","date":"2025-06-05","arxiv_id":"2506.05035","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":13,"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"}}