mlsanityData to 14 Oct 2026

Towards Balancing Preference and Performance through Adaptive Personalized Explainability

arXiv 2504.13856 ↗First posted 21 Mar 2025cs.HC cs.AI cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

As robots and digital assistants are deployed in the real world, these agents must be able to communicate their decision-making criteria to build trust, improve human-robot teaming, and enable collaboration. While the field of explainable artificial intelligence (xAI) has made great strides to enable such communication, these advances often assume that one xAI approach is ideally suited to each problem (e.g., decision trees to explain how to triage patients in an emergency or feature-importance maps to explain radiology reports). This fails to recognize that users have diverse experiences or preferences for interaction modalities. In this work, we present two user-studies set in a simulated autonomous vehicle (AV) domain. We investigate (1) population-level preferences for xAI and (2) personalization strategies for providing robot explanations. We find significant differences between xAI modes (language explanations, feature-importance maps, and decision trees) in both preference (p < 0.01) and performance (p < 0.05). We also observe that a participant's preferences do not always align with their performance, motivating our development of an adaptive personalization strategy to balance the two. We show that this strategy yields significant performance gains (p < 0.05), and we conclude with a discussion of our findings and implications for xAI in human-robot interactions.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 50 of its 116 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

50 of 116 references.

References · 50

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  5. 2019Attention is not Explanationcited by 929
  6. 2019Attention is not not Explanationcited by 636
  7. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  8. 2019Federated Learning with Personalization Layerscited by 541
  9. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  10. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  11. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  12. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
38 more
  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  2. 2020Adaptive Personalized Federated Learningcited by 358
  3. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  4. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  5. 2018Metrics for Explainable AI: Challenges and Prospectscited by 260
  6. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  7. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 253
  8. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  9. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 234
  10. 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
  11. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 190
  12. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  13. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  14. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 123
  15. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  16. 2019Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approachescited by 101
  17. 2018Understanding the Origins of Bias in Word Embeddingscited by 91
  18. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  19. 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
  20. 2021Explanations in Autonomous Driving: A Surveycited by 81
  21. 2022Personalized Prompt Learning for Explainable Recommendationcited by 79
  22. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 64
  23. 2021Explainability Pitfalls: Beyond Dark Patterns in Explainable AIcited by 36
  24. 2021Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recoverycited by 32
  25. 2020Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Mapscited by 30
  26. 2022The Utility of Explainable AI in Ad Hoc Human-Machine Teamingcited by 30
  27. 2023Selective Explanations: Leveraging Human Input to Align Explainable AIcited by 29
  28. 2020Finding Experts in Transformer Modelscited by 28
  29. 2021Generate Natural Language Explanations for Recommendationcited by 23
  30. 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understandingcited by 17
  31. 2019Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrationscited by 14
  32. 2022Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrationscited by 14
  33. 2020Cross-Loss Influence Functions to Explain Deep Network Representationscited by 12
  34. 2019Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviorscited by 9
  35. 2021Personalized Federated Deep Learning for Pain Estimation From Face Imagescited by 8
  36. 2021Spatio-Temporal Split Learningcited by 7
  37. 2022Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systemscited by 6
  38. 2023Towards Reconciling Usability and Usefulness of Explainable AI Methodologiescited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2025Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimizationcited by 2
  2. 2026PONTE: Personalized Orchestration for Natural Language Trustworthy Explanationscited by 1
  3. 2025Personalised Explanations in Long-term Human-Robot Interactionscited by 0