Explanation in Artificial Intelligence: Insights from the Social Sciences
Explore this paper's citation graph
Summary
This paper argues that the field of explainable artificial intelligence should build on existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics, and draws out some important findings.
- Type
- preprint
- Published
- 2017-06-22
- Cited by
- 5,593
- References
- 200
- Access
- Open access
- OpenAlex
- https://openalex.org/W2670253439
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:36024272
Keywords
Intuition, Cognition, Field (mathematics), Process (computing), Psychology
References
- Situation Awareness-Based Agent Transparency
- Explanation in Science
- Explanation and inference: mechanistic and functional explanations guide property generalization
- Dialogical Models of Explanation
- A Probabilistic Model of Plan Recognition
- Computational Complexity of Hypothesis Assembly
- A Knowledge-Level Account of Abduction
- Explanatory Coherence and Belief Revision in Naive Physics
- Types of Explanations.
- Counterfactuals, conditionals and causality: A social psychological perspective
- Automated planning - theory and practice
- Explanation and interaction - the computer generation of explanatory dialogues
- Causes and explanations in the structural-model approach: Tractable cases
- An enquiry concerning human understanding : a critical edition
- From Understanding Computation to Understanding Neural Circuitry
- Abductive inference : computation, philosophy, technology
- The MYCIN Experiments of the Stanford Heuristic Programming Project
- Four decades of scientific explanation
- Logical dialogue-games and fallacies
- Causal schemata and the attribution process
Cited by
- Deep Reinforcement Learning: An Overview
- Interpretable R-CNN
- Automated classification of adverse events in pharmacovigilance
- Network Analysis for Explanation
- Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers
- Plan Explanations as Model Reconciliation
- Explainable Software Analytics
- Manipulating and Measuring Model Interpretability
- Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations
- Intelligible Artificial Intelligence
- People's Judgments of Human and Robot Behaviors: A Robust Set of Behaviors and Some Discrepancies
- The Design and Validation of an Intuitive Confidence Measure
- Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda
- A review of possible effects of cognitive biases on interpretation of rule-based machine learning models
- Explainable Recommendation: A Survey and New Perspectives
- Semantic Explanations of Predictions
- Ethics by Design: Necessity or Curse?
- Teaching Meaningful Explanations
- Hierarchical Expertise Level Modeling for User Specific Contrastive Explanations
- Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
Related papers
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier
- Towards A Rigorous Science of Interpretable Machine Learning
- The mythos of model interpretability
- Examples are not enough, learn to criticize! Criticism for Interpretability
- European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation"
- Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
- Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
- Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda