mlsanityData to 7 Oct 2026

Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making

arXiv 2301.05809 ↗First posted 14 Jan 2023cs.HC cs.AI cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confidence indicating AI's correctness likelihood (CL) but ignored humans' CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans' appropriate trust based on the CL of both sides at a task-instance level. We first modeled humans' CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and effectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users' trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confidence. We further provided practical implications for more human-compatible AI-assisted decision-making.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 28 of its 111 references that are in the map. First posted on arXiv 14 Jan 2023.

Builds on

28 of 111 references.

References · 28

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  4. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  5. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  6. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  7. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  8. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
  9. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
  10. 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
  11. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 138
  12. 2020Learning to Complement Humanscited by 123
16 more
  1. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  2. 2021To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingcited by 118
  3. 2018'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisionscited by 91
  4. 2020"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humanscited by 86
  5. 2022Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderationcited by 66
  6. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
  7. 2020Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-makingcited by 59
  8. 2022Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learningcited by 53
  9. 2021Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactionscited by 35
  10. 2022Who Goes First? Influences of Human-AI Workflow on Decision Making in Clinical Imagingcited by 32
  11. 2021Teaching Humans When To Defer to a Classifier via Exemplarscited by 29
  12. 2022Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Workcited by 15
  13. 2018On Cognitive Preferences and the Plausibility of Rule-based Modelscited by 14
  14. 2019Expert-Augmented Machine Learningcited by 12
  15. 2015Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Modelscited by 11
  16. 2020Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamworkcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 20; 2025: 22; 2026: 18.

67 papers.

Sort:

By area:

  1. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  2. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  3. 2024Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Makingcited by 38
  4. 2024Complementarity in Human-AI Collaboration: Concept, Sources, and Evidencecited by 35
  5. 2024A Decision Theoretic Framework for Measuring AI Reliancecited by 26
  6. 2023A Diachronic Perspective on User Trust in AI under Uncertaintycited by 23
  7. 2023A Systematic Review on Fostering Appropriate Trust in Human-AI Interactioncited by 21
  8. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
  9. 2025As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Makingcited by 18
  10. 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
  11. 2026Intelligent AI Delegationcited by 16
  12. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
38 more
  1. 2024Does More Advice Help? The Effects of Second Opinions in AI-Assisted Decision Makingcited by 14
  2. 2024Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learningcited by 13
  3. 2024Modulating Language Model Experiences through Frictionscited by 13
  4. 2025AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depressioncited by 13
  5. 2025Mapping Caregiver Needs to AI Chatbot Design: Strengths and Gaps in Mental Health Support for Alzheimer's and Dementia Caregiverscited by 13
  6. 2024How should AI decisions be explained? Requirements for Explanations from the Perspective of European Lawcited by 10
  7. 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
  8. 2023Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AIcited by 9
  9. 2024Decoding AI's Nudge: A Unified Framework to Predict Human Behavior in AI-assisted Decision Makingcited by 9
  10. 2024Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scarycited by 9
  11. 2025From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysiscited by 9
  12. 2025Measuring and mitigating overreliance to build human-compatible AIcited by 9
  13. 2024Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with Studentscited by 8
  14. 2024Understanding the Effects of Miscalibrated AI Confidence on User Trust, Reliance, and Decision Efficacycited by 6
  15. 2025Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistancecited by 6
  16. 2023May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainabilitycited by 5
  17. 2024Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Makingcited by 5
  18. 2026Epistemology gives a Future to Complementarity in Human-AI Interactionscited by 5
  19. 2025How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyondcited by 4
  20. 2025Towards Uncertainty Aware Task Delegation and Human-AI Collaborative Decision-Makingcited by 4
  21. 2023Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Reviewcited by 3
  22. 2024Explainable and Human-Grounded AI for Decision Support Systems: The Theory of Epistemic Quasi-Partnershipscited by 3
  23. 2025Less or More: Towards Glanceable Explanations for LLM Recommendations Using Ultra-Small Devicescited by 3
  24. 2025Human-AI Complementarity: A Goal for Amplified Oversightcited by 3
  25. 2024Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Correctionscited by 2
  26. 2025The Impact and Feasibility of Self-Confidence Shaping for AI-Assisted Decision-Makingcited by 2
  27. 2025On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomycited by 2
  28. 2026Incentive-Tuning: Understanding and Designing Incentives for Empirical Human-AI Decision-Making Studiescited by 2
  29. 2024Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstructioncited by 1
  30. 2025Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspectivecited by 1
  31. 2025Exploring the Impact of Explainable AI and Cognitive Capabilities on Users' Decisionscited by 1
  32. 2025Bayesian Inference for Correlated Human Experts and Classifierscited by 1
  33. 2025Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Studycited by 1
  34. 2025"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussionscited by 1
  35. 2026A Checklist for Trustworthy, Safe, and User-Friendly Mental Health Chatbotscited by 1
  36. 2026Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learnedcited by 1
  37. 2026Towards an Appropriate Level of Reliance on AI: A Preliminary Reliance-Control Framework for AI in Software Engineeringcited by 1
  38. 2024Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcarecited by 0

50 most cited of 67 All 67 (JSON)