{"url":"/method/lime","slug":"lime","name":"LIME","full_name":"Local Interpretable Model-Agnostic Explanations","full_name_withheld":false,"description_markdown":"**LIME**, or **Local Interpretable Model-Agnostic Explanations**, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by approximating it locally with an interpretable model. It modifies a single data sample by tweaking the feature values and observes the resulting impact on the output. It performs the role of an \"explainer\" to explain predictions from each data sample. The output of LIME is a set of explanations representing the contribution of each feature to a prediction for a single sample, which is a form of local interpretability.\r\n\r\nInterpretable models in LIME can be, for instance, [linear regression](https://paperswithcode.com/method/linear-regression) or decision trees, which are trained on small perturbations (e.g. adding noise, removing words, hiding parts of the image) of the original model to provide a good local approximation.","description_state":"present","introduced_year":null,"introduced_by":{"title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","paper":"/paper/why-should-i-trust-you-explaining-the","first_author":"Marco Tulio Ribeiro","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/why-should-i-trust-you-explaining-the"},"source":{"url":"http://arxiv.org/abs/1602.04938v3","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/marcotcr/lime","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Interpretability","url":"/methods/category/interpretability","pwc_aliases":[]}],"n_papers_tagged":378,"archive_num_papers":378,"papers_newest_first":[{"paper":"/paper/robustness-of-misinformation-classification","title":"Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack","date":"2025-06-30","arxiv_id":"2506.23661","n_code_links":1,"syntology":null},{"paper":null,"title":"Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning","date":"2025-06-26","arxiv_id":"2506.20916","n_code_links":0,"syntology":null},{"paper":null,"title":"IXAII: An Interactive Explainable Artificial Intelligence Interface for Decision Support Systems","date":"2025-06-26","arxiv_id":"2506.21310","n_code_links":0,"syntology":null},{"paper":null,"title":"Analyzing Emotions in Bangla Social Media Comments Using Machine Learning and LIME","date":"2025-06-11","arxiv_id":"2506.10154","n_code_links":0,"syntology":null},{"paper":null,"title":"Local MDI+: Local Feature Importances for Tree-Based Models","date":"2025-06-10","arxiv_id":"2506.08928","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comprehensive Analysis of COVID-19 Detection Using Bangladeshi Data and Explainable AI","date":"2025-06-08","arxiv_id":"2506.07234","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100","date":"2025-06-01","arxiv_id":"2506.06345","n_code_links":0,"syntology":null},{"paper":"/paper/difflime-enhancing-explainability-with-a","title":"DiffLIME: Enhancing Explainability with a Diffusion-Based LIME Algorithm for Fault Diagnosis","date":"2025-05-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Interpretable phenotyping of Heart Failure patients with Dutch discharge letters","date":"2025-05-30","arxiv_id":"2505.24619","n_code_links":0,"syntology":null},{"paper":"/paper/multi-criteria-rank-based-aggregation-for","title":"Multi-criteria Rank-based Aggregation for Explainable AI","date":"2025-05-30","arxiv_id":"2505.24612","n_code_links":1,"syntology":null},{"paper":"/paper/mlran-a-behavioural-dataset-for-ransomware","title":"MLRan: A Behavioural Dataset for Ransomware Analysis and Detection","date":"2025-05-24","arxiv_id":"2505.18613","n_code_links":1,"syntology":null},{"paper":null,"title":"Towards Trustworthy Keylogger detection: A Comprehensive Analysis of Ensemble Techniques and Feature Selections through Explainable AI","date":"2025-05-22","arxiv_id":"2505.16103","n_code_links":0,"syntology":null},{"paper":null,"title":"Comprehensive Lung Disease Detection Using Deep Learning Models and Hybrid Chest X-ray Data with Explainable AI","date":"2025-05-21","arxiv_id":"2505.16028","n_code_links":0,"syntology":null},{"paper":null,"title":"CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data","date":"2025-05-20","arxiv_id":"2505.14027","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable AI for Securing Healthcare in IoT-Integrated 6G Wireless Networks","date":"2025-05-20","arxiv_id":"2505.14659","n_code_links":0,"syntology":null},{"paper":"/paper/2505-11210","title":"Minimizing False-Positive Attributions in Explanations of Non-Linear Models","date":"2025-05-16","arxiv_id":"2505.11210","n_code_links":1,"syntology":{"ran":0,"of":11,"unverified":11,"pointer_only":0}},{"paper":null,"title":"Enhanced Photonic Chip Design via Interpretable Machine Learning Techniques","date":"2025-05-14","arxiv_id":"2505.09266","n_code_links":0,"syntology":null},{"paper":null,"title":"Deeply Explainable Artificial Neural Network","date":"2025-05-10","arxiv_id":"2505.06731","n_code_links":0,"syntology":null},{"paper":null,"title":"Interactive Diabetes Risk Prediction Using Explainable Machine Learning: A Dash-Based Approach with SHAP, LIME, and Comorbidity Insights","date":"2025-05-08","arxiv_id":"2505.05683","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Convolutional Neural Networks for Rice Grain Classification: An Explainable AI Approach","date":"2025-05-07","arxiv_id":"2505.05513","n_code_links":0,"syntology":null},{"paper":null,"title":"Understanding the Mechanisms Behind Structural Influences on Link Prediction: A Case Study on FB15k-237","date":"2025-05-03","arxiv_id":"2505.01655","n_code_links":0,"syntology":null},{"paper":null,"title":"Machine Learning Meets Transparency in Osteoporosis Risk Assessment: A Comparative Study of ML and Explainability Analysis","date":"2025-05-01","arxiv_id":"2505.00410","n_code_links":0,"syntology":null},{"paper":"/paper/newton-puiseux-analysis-for-interpretability","title":"Newton-Puiseux Analysis for Interpretability and Calibration of Complex-Valued Neural Networks","date":"2025-04-27","arxiv_id":"2504.19176","n_code_links":1,"syntology":null},{"paper":null,"title":"An Explainable Nature-Inspired Framework for Monkeypox Diagnosis: Xception Features Combined with NGBoost and African Vultures Optimization Algorithm","date":"2025-04-24","arxiv_id":"2504.17540","n_code_links":0,"syntology":null},{"paper":null,"title":"What Makes for a Good Saliency Map? Comparing Strategies for Evaluating Saliency Maps in Explainable AI (XAI)","date":"2025-04-23","arxiv_id":"2504.17023","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content","date":"2025-04-18","arxiv_id":"2504.13545","n_code_links":0,"syntology":null},{"paper":"/paper/long-context-non-factoid-question-answering","title":"Long-context Non-factoid Question Answering in Indic Languages","date":"2025-04-18","arxiv_id":"2504.13615","n_code_links":1,"syntology":null},{"paper":null,"title":"Which LIME should I trust? Concepts, Challenges, and Solutions","date":"2025-03-31","arxiv_id":"2503.24365","n_code_links":0,"syntology":null},{"paper":null,"title":"MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study","date":"2025-03-25","arxiv_id":"2503.20758","n_code_links":0,"syntology":null},{"paper":null,"title":"EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability","date":"2025-03-22","arxiv_id":"2503.20796","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/xai","name":"Explainable Artificial Intelligence (XAI)","papers":60},{"task":"/task/explainable-artificial-intelligence","name":"Explainable artificial intelligence","papers":51},{"task":"/task/feature-importance","name":"Feature Importance","papers":49},{"task":"/task/decision-making","name":"Decision Making","papers":44},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":29},{"task":"/task/image-classification","name":"Image Classification","papers":24},{"task":"/task/image-classification","name":"image-classification","papers":24},{"task":null,"name":"counterfactual","papers":22},{"task":"/task/classification-1","name":"Classification","papers":17},{"task":"/task/regression-1","name":"regression","papers":15},{"task":"/task/diagnostic","name":"Diagnostic","papers":14},{"task":"/task/interpretable-machine-learning","name":"Interpretable Machine Learning","papers":14},{"task":"/task/text-classification","name":"Text Classification","papers":14},{"task":"/task/text-classification-1","name":"text-classification","papers":14},{"task":"/task/fairness","name":"Fairness","papers":11},{"task":"/task/feature-selection","name":"feature selection","papers":11},{"task":"/task/deep-learning","name":"Deep Learning","papers":10},{"task":"/task/prediction","name":"Prediction","papers":10},{"task":"/task/model","name":"model","papers":10},{"task":"/task/management","name":"Management","papers":9}],"tasks_shown":20,"n_tasks":228,"usage_by_year":[{"year":"2016","papers":4},{"year":"2017","papers":2},{"year":"2018","papers":13},{"year":"2019","papers":22},{"year":"2020","papers":51},{"year":"2021","papers":57},{"year":"2022","papers":45},{"year":"2023","papers":62},{"year":"2024","papers":75},{"year":"2025","papers":47}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/lime"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}