mlsanityData to 7 Oct 2026

The Challenge of Crafting Intelligible Intelligence

arXiv 1803.04263 ↗First posted 9 Mar 2018cs.AIcited by 46

Not on the map. Why?

Abstract (arXiv)

Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make AI intelligible, either by using inherently interpretable models or by developing new methods for explaining and controlling otherwise overwhelmingly complex decisions using local approximation, vocabulary alignment, and interactive explanation. This paper argues that intelligibility is essential, surveys recent work on building such systems, and highlights key directions for research.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 13; 2023: 8; 2024: 9; 2025: 5.

46 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2021Expanding Explainability: Towards Social Transparency in AI systemscited by 124
  3. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  4. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 65
  5. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  6. 2023In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Makingcited by 50
  7. 2025LLMs for Explainable AI: A Comprehensive Surveycited by 42
  8. 2022Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AIcited by 40
  9. 2021Explaining a Series of Models by Propagating Shapley Valuescited by 37
  10. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  11. 2022Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theorycited by 32
  12. 2021Nonperturbative renormalization for the neural network-QFT correspondencecited by 24
34 more
  1. 2022A Computational Inflection for Scientific Discoverycited by 22
  2. 2022On the Influence of Explainable AI on Automation Biascited by 18
  3. 2021From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidencecited by 17
  4. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
  5. 2021Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligencecited by 13
  6. 2021Efficient Explanations With Relevant Setscited by 12
  7. 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanationscited by 11
  8. 2021Efficient Explanations for Knowledge Compilation Languagescited by 9
  9. 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
  10. 2023Why is plausibility surprisingly problematic as an XAI criterion?cited by 9
  11. 2023What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systemscited by 9
  12. 2022Mediators: Conversational Agents Explaining NLP Model Behaviorcited by 7
  13. 2022Renormalization in the neural network-quantum field theory correspondencecited by 7
  14. 2023Understanding Practices around Computational News Discovery Tools in the Domain of Science Journalismcited by 7
  15. 2024CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systemscited by 5
  16. 2024A Fuzzy-based Approach to Predict Human Interaction by Functional Near-Infrared Spectroscopycited by 4
  17. 2023A User Study on Explainable Online Reinforcement Learning for Adaptive Systemscited by 3
  18. 2021Toward Affective XAI: Facial Affect Analysis for Understanding Explainable Human-AI Interactionscited by 2
  19. 2022Topological Representations of Local Explanationscited by 2
  20. 2022On Deciding Feature Membership in Explanations of SDD & Related Classifierscited by 2
  21. 2023Reason to explain: Interactive contrastive explanations (REASONX)cited by 2
  22. 2024Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Modelscited by 2
  23. 2024Towards a Unified Framework for Evaluating Explanationscited by 2
  24. 2022Subgroup Discovery in Unstructured Datacited by 1
  25. 2024BANSAI: Towards Bridging the AI Adoption Gap in Industrial Robotics with Neurosymbolic Programmingcited by 1
  26. 2024Automated Explanation Selection for Scientific Discoverycited by 1
  27. 2025AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaborationcited by 1
  28. 2025Towards Transparent Ethical AI: A Roadmap for Trustworthy Robotic Systemscited by 1
  29. 2022Physical Activity Recognition by Utilising Smartphone Sensor Signalscited by 0
  30. 2022What Do End-Users Really Want? Investigation of Human-Centered XAI for Mobile Health Appscited by 0
  31. 2024Interaction as Explanation: A User Interaction-based Method for Explaining Image Classification Modelscited by 0
  32. 2024Composers' Evaluations of an AI Music Tool: Insights for Human-Centred Designcited by 0
  33. 2025The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPRcited by 0
  34. 2025What Do People Want to Know About Artificial Intelligence (AI)? The Importance of Answering End-User Questions to Explain Autonomous Vehicle (AV) Decisionscited by 0