mlsanityData to 7 Oct 2026

An Information Bottleneck Characterization of the Understanding-Workload Tradeoff

arXiv 2310.07802 ↗First posted 11 Oct 2023cs.AI cs.HCcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human understanding, is central to effective XAI design. Existing work in XAI has demonstrated a tradeoff between understanding and workload induced by different types of explanations. Explaining complex concepts through abstractions (hand-crafted groupings of related problem features) has been shown to effectively address and balance this workload-understanding tradeoff. In this work, we characterize the workload-understanding balance via the Information Bottleneck method: an information-theoretic approach which automatically generates abstractions that maximize informativeness and minimize complexity. In particular, we establish empirical connections between workload and complexity and between understanding and informativeness through human-subject experiments. This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 95 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

29 of 95 references.

References · 29

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  5. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  6. 2018Sanity Checks for Saliency Mapscited by 1,149
  7. 2016Deep Variational Information Bottleneckcited by 915
  8. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  9. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  10. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  11. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
  12. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
17 more
  1. 2017Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciencescited by 84
  2. 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
  3. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  4. 2016The deterministic information bottleneckcited by 42
  5. 2017Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanationscited by 37
  6. 2020Understanding Learned Reward Functionscited by 37
  7. 2019Explaining a black-box using Deep Variational Information Bottleneck Approachcited by 35
  8. 2017Enabling Robots to Communicate their Objectivescited by 34
  9. 2023Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAIcited by 33
  10. 2020Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Mapscited by 30
  11. 2022The Utility of Explainable AI in Ad Hoc Human-Machine Teamingcited by 30
  12. 2023Selective Explanations: Leveraging Human Input to Align Explainable AIcited by 29
  13. 2019Explaining Reinforcement Learning to Mere Mortals: An Empirical Studycited by 21
  14. 2019Semantic categories of artifacts and animals reflect efficient codingcited by 13
  15. 2018Plan Explanations as Model Reconciliation -- An Empirical Studycited by 7
  16. 2022Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learningcited by 6
  17. 2019Online Explanation Generation for Human-Robot Teamingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentscited by 6
  2. 2026PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&Acited by 2
  3. 2025Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Makingcited by 0