TED: Teaching AI to Explain its Decisions

Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.

• Publication year

  2018

• Venue

  AAAI/ACM Conference on AI, Ethics, and Society

• Publication date

  2018-11-12

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3306618.3314273arXiv 1811.04896
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning

  2019cited by this paper
• Boolean Decision Rules via Column Generation

  2018cited by this paper
• General Data Protection Regulation

  2018cited by this paper
• Transparent, explainable, and accountable AI for robotics

  2017cited by this paper
• Explanation and Justification in Machine Learning : A Survey Or

  2017cited by this paper
• 2017 Annual Report

  2017cited by this paper
• Methods for interpreting and understanding deep neural networks

  2017cited by this paper
• Accountability of AI Under the Law: The Role of Explanation

  2017influential reference
• A Formal Framework to Characterize Interpretability of Procedures

  2017cited by this paper
• Towards A Rigorous Science of Interpretable Machine Learning

  2017cited by this paper
• A Unified Approach to Interpreting Model Predictions

  2017cited by this paper
• Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences

  2017influential reference
• Explanation in Artificial Intelligence: Insights from the Social Sciences

  2017cited by this paper
• Interpreting Blackbox Models via Model Extraction

  2017cited by this paper
• "Meaningful Information" and the Right to Explanation

  2017cited by this paper
• Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection Regulation

  2017influential reference
• AI Now 2017 Report

  2017cited by this paper
• Generating Visual Explanations

  2016influential reference
• Joint Learning of Semantic and Latent Attributes

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

  2016cited by this paper
• EU regulations on algorithmic decision-making and a "right to explanation"

  2016influential reference
• The mythos of model interpretability

  2016cited by this paper
• Why Is That Relevant? Collecting Annotator Rationales for Relevance Judgments

  2016influential reference
• Rationale-Augmented Convolutional Neural Networks for Text Classification

  2016cited by this paper
• Rationalizing Neural Predictions

  2016cited by this paper
• Engineering safety in machine learning

  2016cited by this paper
• Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission

  2015cited by this paper
• Deep Learning

  2015cited by this paper
• Too much, too little, or just right? Ways explanations impact end users' mental models

  2013cited by this paper
• Discovering localized attributes for fine-grained recognition

  2012cited by this paper
• Annotator rationales for visual recognition

  2011cited by this paper
• Automatically Generating Annotator Rationales to Improve Sentiment Classification

  2010cited by this paper
• Modeling Annotators: A Generative Approach to Learning from Annotator Rationales

  2008influential reference
• Simplicity and probability in causal explanation.

  2007cited by this paper
• Using “Annotator Rationales” to Improve Machine Learning for Text Categorization

  2007cited by this paper
• Explanation-Augmented SVM: an approach to incorporating domain knowledge into SVM learning

  2005cited by this paper

• Ethical theories, governance models, and strategic frameworks for responsible AI adoption and organizational success

  2025cites this paper
• Effectiveness of Explainable Artificial Intelligence (XAI) Techniques for Improving Human Trust in Machine Learning Models: A Systematic Literature Review

  2025cites this paper
• Interpretability and accuracy of machine learning algorithms for biomedical time series analysis - a scoping review

  2025cites this paper
• Explainable AI the Latest Advancements and New Trends

  2025cites this paper
• Artificial intelligence-driven advances in nuclear technology: Exploring innovations, applications, and future prospects

  2025cites this paper
• Transistor-to-Package Thermal Simulation with Hotspot Mitigation by Decoupling

  2025cites this paper
• Augmenting Intelligence: A Hybrid Framework for Scalable and Stable Explanations

  2025influential citation
• The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance

  2025cites this paper
• CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions

  2025cites this paper
• DEAL: Disentangle and Localize Concept-level Explanations for VLMs

  2024cites this paper
• Interpretability of deep neural networks: A review of methods, classification and hardware

  2024cites this paper
• BEOL Layout Optimization to Improve RF Performance of 40nm Node Technology for High-Frequency Applications

  2024cites this paper
• Challenging the Human-in-the-loop in Algorithmic Decision-making

  2024cites this paper
• Deepthreatexplainer: a united explainable predictor for threat comments identification on Twitter

  2024cites this paper
• eXplainable Random Forest

  2024cites this paper
• AI in terrorism sentencing: evaluating predictive accuracy and ethical implications

  2024cites this paper
• Explainable AI: definition and attributes of a good explanation for health AI

  2024cites this paper
• Explainable AI for All - a Roadmap for Inclusive XAI for people with Cognitive Disabilities

  2024cites this paper
• Explainable AI for Text Classification: Lessons from a Comprehensive Evaluation of Post Hoc Methods

  2024cites this paper
• Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study

  2024cites this paper
• Dual-Cloud Multi-Secret Sharing Architecture for Privacy Preserving Persistent Computation

  2024cites this paper
• TrustML: A Python package for computing the trustworthiness of ML models

  2024cites this paper
• Are Data-Driven Explanations Robust Against Out-of-Distribution Data?

  2023cites this paper
• Designing interpretable ML system to enhance trust in healthcare: A systematic review to proposed responsible clinician-AI-collaboration framework

  2023cites this paper
• SHAP-based Explanations to Improve Classification Systems

  2023cites this paper
• A Critical Survey on Fairness Benefits of XAI

  2023cites this paper
• Cardiovascular disease identification using a hybrid CNN-LSTM model with explainable AI

  2023cites this paper
• Explainable AI: roles and stakeholders, desirements and challenges

  2023cites this paper
• ForestMonkey: Toolkit for Reasoning with AI-Based Defect Detection and Classification Models

  2023cites this paper
• Impact of Feature Encoding on Malware Classification Explainability

  2023cites this paper
• Strategies to exploit XAI to improve classification systems

  2023cites this paper
• The Role of Explainable AI in the Research Field of AI Ethics

  2023cites this paper
• Enhancing Hate Speech Detection through Explainable AI

  2023cites this paper
• Explanation Ontology: A general-purpose, semantic representation for supporting user-centered explanations

  2023cites this paper
• Evaluating machine-generated explanations: a “Scorecard” method for XAI measurement science

  2023cites this paper
• Explainability and white box in drug discovery

  2023cites this paper
• Meta-analysis informed machine learning: Supporting cytokine storm detection during CAR-T cell Therapy

  2023cites this paper
• Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence

  2023cites this paper
• A multi-institutional study using artificial intelligence to provide reliable and fair feedback to surgeons

  2023cites this paper
• A Critical Survey on Fairness Benefits of Explainable AI

  2023cites this paper
• An Explainable AI approach towards Epileptic Seizure Detection

  2022cites this paper
• Human-AI Collaboration for UX Evaluation: Effects of Explanation and Synchronization

  2022cites this paper
• Explanatory Learning: Beyond Empiricism in Neural Networks

  2022cites this paper
• Relation between prognostics predictor evaluation metrics and local interpretability SHAP values

  2022cites this paper
• On the Suitability of SHAP Explanations for Refining Classifications

  2022cites this paper
• Study of Feature Importance for Quantum Machine Learning Models

  2022cites this paper
• Human-centered explainability for life sciences, healthcare, and medical informatics

  2022cites this paper
• Perspectives on incorporating expert feedback into model updates

  2022cites this paper
• Socially Intelligent Genetic Agents for the Emergence of Explicit Norms

  2022cites this paper
• Explaining Artificial Intelligence Generation and Creativity: Human interpretability for novel ideas and artifacts

  2022cites this paper
• Explanatory machine learning for sequential human teaching

  2022cites this paper
• Linked Open Government Data to Predict and Explain House Prices: The Case of Scottish Statistics Portal

  2022cites this paper
• Review on Interpretable Machine Learning in Smart Grid

  2022cites this paper
• An integrated approach explaining the detection of distributed denial of service attacks

  2022cites this paper
• Social Media Hate Speech Detection Using Explainable Artificial Intelligence (XAI)

  2022cites this paper
• Enhancing Cluster Analysis With Explainable AI and Multidimensional Cluster Prototypes

  2022cites this paper
• Towards Prototype-Based Self-Explainable Graph Neural Network

  2022cites this paper
• Trust Metrics for Medical Deep Learning Using Explainable-AI Ensemble for Time Series Classification

  2022cites this paper
• Practical Control Design for the Deep Learning Age: Distillation of Deep RL-Based Controllers

  2022cites this paper
• Explainable software systems: from requirements analysis to system evaluation

  2022cites this paper
• A review of AI teaching and learning from 2000 to 2020

  2022cites this paper
• ISO/IEC 25000 and AI product quality measurement perspectives

  2022cites this paper
• What Do We Want From Explainable Artificial Intelligence (XAI)?

  2021cites this paper
• What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

  2021cites this paper
• Explainable AI for B5G/6G: Technical Aspects, Use Cases, and Research Challenges

  2021cites this paper
• Image Classification with Consistent Supporting Evidence

  2021cites this paper
• How to Explain It to Facility Managers? A Qualitative, Industrial User Research Study for Explainability

  2021cites this paper
• Expanding Explainability: Towards Social Transparency in AI systems

  2021cites this paper
• The Stakeholder Playbook for Explaining AI Systems

  2021cites this paper
• A novel model usability evaluation framework (MUsE) for explainable artificial intelligence

  2021cites this paper
• Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

  2021cites this paper
• Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable

  2021cites this paper
• Explainable artificial intelligence: a comprehensive review

  2021cites this paper
• AI Explainability 360: Impact and Design

  2021cites this paper
• Human-Centered Explainable AI (XAI): From Algorithms to User Experiences

  2021cites this paper
• Towards Self-Explainable Graph Neural Network

  2021cites this paper
• Harnessing value from data science in business: ensuring explainability and fairness of solutions

  2021cites this paper
• Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models

  2021cites this paper
• Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue

  2021cites this paper
• Rational AI: A comparison of human and AI responses to triggers of economic irrationality in poker

  2021cites this paper
• Towards Explainable Image Classifier: An Analogy to Multiple Choice Question Using Patch-level Similarity Measure

  2021cites this paper
• Designer-User Communication for XAI: An epistemological approach to discuss XAI design

  2021cites this paper
• A Review on Explainability in Multimodal Deep Neural Nets

  2021cites this paper
• XAI for Operations in the Process Industry - Applications, Theses, and Research Directions

  2021influential citation
• Explainability-aided Domain Generalization for Image Classification

  2021cites this paper
• Human-AI Collaboration for UX Evaluation: Effects of Explanation and Synchronization

  2021cites this paper
• Learning to predict with supporting evidence: applications to clinical risk prediction

  2021cites this paper
• Benchmarking and survey of explanation methods for black box models

  2021cites this paper
• Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition

  2020cites this paper
• Explainable Deep Learning: A Field Guide for the Uninitiated

  2020cites this paper
• xCos: An Explainable Cosine Metric for Face Verification Task

  2020cites this paper
• Arbiter: A Domain-Specific Language for Ethical Machine Learning

  2020cites this paper
• Consumer-Driven Explanations for Machine Learning Decisions: An Empirical Study of Robustness

  2020influential citation
• Fairness-Aware Machine Learning An Extensive Overview

  2020cites this paper
• Teaching AI to Explain its Decisions Can Affect Class Balance

  2020influential citation
• Explaining Creative Artifacts

  2020cites this paper
• Beneficial and harmful explanatory machine learning

  2020cites this paper
• Personalising Explainable Recommendations: Literature and Conceptualisation

  2020cites this paper
• AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models

  2020cites this paper
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies

  2020cites this paper