mlsanityData to 7 Oct 2026

Levels of explainable artificial intelligence for human-aligned conversational explanations

arXiv 2107.03178 ↗First posted 7 Jul 2021cs.AI cs.HCcited by 21

Not on the map. Why?

Abstract (arXiv)

Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers for this growth include recent legislative changes and increased investments by industry and governments, along with increased concern from the general public. People are affected by autonomous decisions every day and the public need to understand the decision-making process to accept the outcomes. However, the vast majority of the applications of XAI/IML are focused on providing low-level `narrow' explanations of how an individual decision was reached based on a particular datum. While important, these explanations rarely provide insights into an agent's: beliefs and motivations; hypotheses of other (human, animal or AI) agents' intentions; interpretation of external cultural expectations; or, processes used to generate its own explanation. Yet all of these factors, we propose, are essential to providing the explanatory depth that people require to accept and trust the AI's decision-making. This paper aims to define levels of explanation and describe how they can be integrated to create a human-aligned conversational explanation system. In so doing, this paper will survey current approaches and discuss the integration of different technologies to achieve these levels with Broad eXplainable Artificial Intelligence (Broad-XAI), and thereby move towards high-level `strong' explanations.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 49 of its 251 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

49 of 251 references.

References · 49

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  5. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  6. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  9. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  10. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  11. 2017Deep Reinforcement Learning: An Overviewcited by 327
  12. 2018Deep Facial Expression Recognition: A Surveycited by 269
37 more
  1. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  2. 2018Human Action Recognition and Prediction: A Surveycited by 226
  3. 2018Machine Theory of Mindcited by 222
  4. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  5. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
  6. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  7. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  8. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 171
  9. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  10. 2016Generating Visual Explanationscited by 156
  11. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 128
  12. 2019Towards Explainable Artificial Intelligencecited by 106
  13. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 96
  14. 2017Explaining Recurrent Neural Network Predictions in Sentiment Analysiscited by 87
  15. 2017Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciencescited by 84
  16. 2016Multi-Objective Deep Reinforcement Learningcited by 81
  17. 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
  18. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  19. 2016Going Deeper into Action Recognition: A Surveycited by 55
  20. 2019Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methodscited by 55
  21. 2017Interpretable & Explorable Approximations of Black Box Modelscited by 54
  22. 2019Pedestrian Attribute Recognition: A Surveycited by 49
  23. 2018Survey on Emotional Body Gesture Recognitioncited by 47
  24. 2019Recent Trends in Deep Learning Based Personality Detectioncited by 29
  25. 2018A Multi-Objective Deep Reinforcement Learning Frameworkcited by 22
  26. 2017Emotion in Reinforcement Learning Agents and Robots: A Surveycited by 21
  27. 2016Towards Transparent AI Systems: Interpreting Visual Question Answering Modelscited by 19
  28. 2018Modular Architecture for StarCraft II with Deep Reinforcement Learningcited by 10
  29. 2018Joint Event Detection and Description in Continuous Video Streamscited by 9
  30. 2019A Short Survey On Memory Based Reinforcement Learningcited by 9
  31. 2018Survey on Vision-based Path Predictioncited by 8
  32. 2016Attentive Explanations: Justifying Decisions and Pointing to the Evidencecited by 6
  33. 2013Affect Control Processes: Intelligent Affective Interaction using a Partially Observable Markov Decision Processcited by 5
  34. 2020Tradeoff-Focused Contrastive Explanation for MDP Planningcited by 5
  35. 2015Advances in Human Action Recognition: A Surveycited by 3
  36. 2018Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automationcited by 3
  37. 2018Explanations for Temporal Recommendationscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 5; 2024: 2; 2025: 4; 2026: 1.

21 papers.

Sort:

By area:

  1. 2021Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)cited by 55
  2. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  3. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  4. 2023Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorationscited by 18
  5. 2022Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunitiescited by 12
  6. 2023Causal Explanations for Sequential Decision-Making in Multi-Agent Systemscited by 10
  7. 2022Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicinecited by 8
  8. 2022Mediators: Conversational Agents Explaining NLP Model Behaviorcited by 7
  9. 2023Mind the Gap! Bridging Explainable Artificial Intelligence and Human Understanding with Luhmann's Functional Theory of Communicationcited by 7
  10. 2022Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarioscited by 5
  11. 2022Experiential Explanations for Reinforcement Learningcited by 5
  12. 2023May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainabilitycited by 5
9 more
  1. 2025Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitorscited by 4
  2. 2024Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agentscited by 3
  3. 2025Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviourcited by 3
  4. 2023A Semi-Automated Solution Approach Recommender for a Given Use Case: a Case Study for AI/ML in Oncology via Scopus and OpenAIcited by 2
  5. 2025A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural languagecited by 2
  6. 2025Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Predictioncited by 2
  7. 2022A Time Series Approach to Explainability for Neural Nets with Applications to Risk-Management and Fraud Detectioncited by 0
  8. 2022Explaining Agent's Decision-making in a Hierarchical Reinforcement Learning Scenariocited by 0
  9. 2026Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planningcited by 0