Anchors: High-Precision Model-Agnostic Explanations

We introduce a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, "sufficient" conditions for predictions. We propose an algorithm to efficiently compute these explanations for any black-box model with high-probability guarantees. We demonstrate the flexibility of anchors by explaining a myriad of different models for different domains and tasks. In a user study, we show that anchors enable users to predict how a model would behave on unseen instances with less effort and higher precision, as compared to existing linear explanations or no explanations.

• Publication year

  2018

• Venue

  AAAI Conference on Artificial Intelligence

• Publication date

  2018-04-25

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1609/aaai.v32i1.11491
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Latent Variable Models

  2019cited by this paper
• Model-Agnostic Interpretability of Machine Learning

  2016influential reference
• Interpretable Decision Sets: A Joint Framework for Description and Prediction

  2016cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016influential reference
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model

  2015cited by this paper
• Hidden Technical Debt in Machine Learning Systems

  2015cited by this paper
• Exploring Models and Data for Image Question Answering

  2015cited by this paper
• Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems

  2015cited by this paper
• Visual7W: Grounded Question Answering in Images

  2015cited by this paper
• Towards Universal Paraphrastic Sentence Embeddings

  2015cited by this paper
• Towards Extracting Faithful and Descriptive Representations of Latent Variable Models

  2015cited by this paper
• Supersparse linear integer models for optimized medical scoring systems

  2015cited by this paper
• Grammar as a Foreign Language

  2014cited by this paper
• GloVe: Global Vectors for Word Representation

  2014cited by this paper
• Submodular Function Maximization

  2014cited by this paper
• Falling Rule Lists

  2014cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Information Complexity in Bandit Subset Selection

  2013influential reference
• Leakage in data mining: formulation, detection, and avoidance

  2011cited by this paper
• An Efficient Explanation of Individual Classifications using Game Theory

  2010influential reference
• Why and why not explanations improve the intelligibility of context-aware intelligent systems

  2009cited by this paper
• How to Explain Individual Classification Decisions

  2009influential reference
• Investigating statistical machine learning as a tool for software development

  2008cited by this paper
• Quick Shift and Kernel Methods for Mode Seeking

  2008cited by this paper
• Toward harnessing user feedback for machine learning

  2007cited by this paper
• Multi-Label Classification: An Overview

  2007cited by this paper
• Elements of Information Theory

  2005cited by this paper
• Probabilistic Inductive Logic Programming

  2004cited by this paper
• in Advances in Neural Information Processing

  1989cited by this paper

• DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

  2026cites this paper
• A hybrid intelligent assessment model for English translation education with improved BERT and SVM

  2026cites this paper
• Interpretable Machine Learning for Price Index Forecasting: A Case Study with Rolling Windows and SHAP

  2026cites this paper
• Nam++: achieving interpretability and fairness without sacrificing accuracy through neural additive models with selective feature interactions

  2026cites this paper
• Tracking student progress and generating personalized recommendations using clustering and explainable artificial intelligence

  2026cites this paper
• Evaluating Explainability: A Framework for Systematic Assessment of Explainable AI Features in Medical Imaging

  2026cites this paper
• Mixtures of Transparent Local Models

  2026cites this paper
• Explainable soft-voting classifier for heart disease prediction using SHAP and LIME

  2026cites this paper
• XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction

  2026cites this paper
• Towards Benchmarking AI Explainability

  2026influential citation
• Explainable multi-modal approach for uncovering key predictors of stroke-risk from ECG, EMG, blood pressure, and respiratory signals

  2026cites this paper
• Toward an artifact that designs itself: generative design science research approach

  2026cites this paper
• Clarity in DEM cementation predictions: Integrating automated machine learning and interpretability analysis of shear wave velocity

  2026cites this paper
• Aligned explanations in neural networks

  2026cites this paper
• DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

  2026cites this paper
• Explainable artificial intelligence for molecular design in pharmaceutical research

  2026cites this paper
• Maritime Radar Target Multifeature Detection Optimization Method Under Capability Lower Bound Constraint

  2026cites this paper
• Circuit Representations of Random Forests with Applications to XAI

  2026cites this paper
• Provably Explaining Neural Additive Models

  2026cites this paper
• Toward Deployable Disinformation Defense: Benchmarking Lightweight Transformers on FakeNewsNet

  2026influential citation
• Exploring Personalized Explanation Methods in Fintech Decision-Making Chatbot Based on User Characteristics Using Large Language Model

  2026cites this paper
• A Survey on Explainable AI for Semantic Communication: Architecture, Challenges, and Future Opportunities

  2026cites this paper
• Explainable AI in education: integrating educational domain knowledge into the deep learning model for improved student performance prediction.

  2026cites this paper
• An explainable machine learning framework for identifying left bundle branch block mechanisms via vectorcardiographic features

  2026cites this paper
• BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models

  2026cites this paper
• Heterogeneous GNN-driven and meta-learned architecture for transparent multimodal string similarity estimation

  2026cites this paper
• RA-MD: An RKHS-based adaptive Mahalanobis distance to enhance counterfactual explanations for neural networks

  2026cites this paper
• A Tutorial on Data-Driven Quality-of-Experience Modeling With Explainable Artificial Intelligence

  2026cites this paper
• Interpret When Possible: A Tree-Based Hybrid Framework for Interpretable Classification

  2026cites this paper
• Formally Explaining Decision Tree Models with Answer Set Programming

  2026cites this paper
• Stacking-based heterogeneous genetic programming for interpretable credit risk evaluation

  2026cites this paper
• Improving Compactness and Reducing Ambiguity of CFIRE Rule-Based Explanations

  2026cites this paper
• A systematic review of molecular representation learning foundation models

  2026cites this paper
• Explaining Machine Learning Predictive Models through Conditional Expectation Methods

  2026cites this paper
• HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data

  2026cites this paper
• LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text

  2026cites this paper
• Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism

  2026cites this paper
• Explainable Artificial Intelligence for Deepfake Detection: Pipeline, Open Source and Comparisons

  2026cites this paper
• Aegis: An AI-Driven Governance Framework for Micro-Frontend Architectures using Trust-Based Federated Learning

  2026cites this paper
• Slice and Explain: Logic-Based Explanations for Neural Networks Through Domain Slicing

  2026cites this paper
• Rules or Weights? Comparing User Understanding of Explainable AI Techniques with the Cognitive XAI-Adaptive Model

  2026cites this paper
• Explainable AI for Cloud Intrusion Detection: A User Study of SHAP and LIME in AWS GuardDuty

  2026cites this paper
• Explainable and probabilistic nearshore wave modeling along living shorelines using a CASGP-X framework

  2026cites this paper
• Enhancing trust through a human-center evaluation framework from an accessibility perspective: The case of graph anomaly detection

  2026cites this paper
• Reference Aware Delexicalization (RAD) Framework: Theory Driven Artificial Intelligence Modeling for Domain Generalization

  2026cites this paper
• Explaining explainability: A comprehensive survey on explainable artificial intelligence and relevant industry applications

  2026cites this paper
• Unifying Formal Explanations: A Complexity-Theoretic Perspective

  2026influential citation
• Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy

  2026cites this paper
• Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments

  2026cites this paper
• Learning Conditional Averages

  2026cites this paper
• Interpretable citrus disease classification through GradCAM++ LIME and vision transformer-based deep learning

  2026cites this paper
• LI-HML detector: a unified framework for network traffic attack classification

  2026cites this paper
• Probabilistic Stability Guarantees for Feature Attributions

  2025cites this paper
• Can Interpretability of Deep Learning Models Detect Textual Adversarial Distribution?

  2025cites this paper
• TELL-ME: Toward Personalized Explanations of Large Language Models

  2025cites this paper
• From explainable artificial intelligence to human understanding

  2025cites this paper
• From scientific theory to duality of predictive artificial intelligence models

  2025cites this paper
• Predicting risk of inadequate micronutrient intake with transferable machine learning models

  2025cites this paper
• Explainable AI Framework for Software Defect Prediction

  2025cites this paper
• An Explainable AI Techniques for Advancing Diabetes Prediction Using Machine Learning

  2025cites this paper
• An integrated model to evaluate the transparency in predicting employee churn using explainable artificial intelligence

  2025cites this paper
• The Last Mile in Remote Sensing Poverty Prediction

  2025cites this paper
• Global explainability of a deep abstaining classifier

  2025cites this paper
• CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability

  2025cites this paper
• Am I Being Treated Fairly? A Conceptual Framework for Individuals to Ascertain Fairness

  2025cites this paper
• Computer-aided detection systems based on ballistocardiography signals: A review

  2025cites this paper
• Exploring the potential and limitations of deep learning and explainable AI for longitudinal life course analysis

  2025cites this paper
• Aspect-based sentiment analysis for software requirements elicitation using fine-tuned Bidirectional Encoder Representations from Transformers and Explainable Artificial Intelligence

  2025cites this paper
• State-of-the-Art in Responsible, Explainable, and Fair AI for Medical Image Analysis

  2025cites this paper
• How to safely discard features based on aggregate SHAP values

  2025cites this paper
• Explainable machine learning identifies features and thresholds predictive of immunotherapy response

  2025cites this paper
• A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

  2025cites this paper
• Towards Explainable Medical Machine Reading Comprehension With Rationale Generation

  2025cites this paper
• Which LIME should I trust? Concepts, Challenges, and Solutions

  2025cites this paper
• MI-VFL: Feature discrepancy-aware distributed model interpretation for vertical federated learning

  2025cites this paper
• Evaluating Sensitivity Consistency of Explanations

  2025cites this paper
• Self-Explaining Neural Networks for Business Process Monitoring

  2025influential citation
• Implementing Explainable AI to Enhance Business Decision Making & Bridging the Trust Gap

  2025cites this paper
• Superpoints Guided Local Explanation For Deep 3D Trackers

  2025cites this paper
• GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks

  2025cites this paper
• MindfulLIME: a stable solution for explanations of machine learning models with enhanced localization precision—a medical image case study

  2025cites this paper
• CFIRE: A General Method for Combining Local Explanations

  2025influential citation
• Explanations Go Linear: Post-Hoc Explainability for Tabular Data with Interpretable Meta-Encoding

  2025cites this paper
• Why Does It Look like this? Introducing a Preliminary Framework for Explainable Graph Drawing (XGD)

  2025cites this paper
• An Efficient Compilation-Based Approach to Explaining Random Forests Through Decision Trees

  2025cites this paper
• A graph theoretic approach to assess quality of data for classification task

  2025cites this paper
• Obtaining Example-Based Explanations from Deep Neural Networks

  2025cites this paper
• A Joint Learning Framework for Bridging Defect Prediction and Interpretation

  2025cites this paper
• Transformer Neural Networks for Behavior-Centric Production Forecasting in Unconventional Reservoir

  2025cites this paper
• Comparative Analysis of Perturbation Techniques in LIME for Intrusion Detection Enhancement

  2025cites this paper
• An Explainable AI approach for detecting failures in air pressure systems

  2025cites this paper
• Evaluating LIME and SHAP in Explaining Malnutrition Classification in Children Under Five

  2025cites this paper
• Computing Improved Explanations for Random Forests: k-Majoritary Reasons

  2025cites this paper
• Can LLM Assist in the Evaluation of the Quality of Machine Learning Explanations?

  2025cites this paper
• AP-GRIP evaluation framework for data-driven train delay prediction models: systematic literature review

  2025cites this paper
• An XAI-based meta-parameter tuning for time-series forecasting

  2025cites this paper
• A Comprehensive User-Centric Method for Evaluating and Comparing XAI Explanations

  2025influential citation
• HyConEx: Hypernetwork classifier with counterfactual explanations

  2025cites this paper
• Logic Explanation of AI Classifiers by Categorical Explaining Functors

  2025cites this paper
• Weighted-digraph-guided multi-kernelized learning for outlier explanation

  2025cites this paper