Overconfident and Unconfident AI Hinder Human-AI Collaboration

• URL: http://arxiv.org/abs/2402.07632v3
• Date: Wed, 17 Apr 2024 18:37:12 GMT
• Title: Overconfident and Unconfident AI Hinder Human-AI Collaboration
• Authors: Jingshu Li, Yitian Yang, Renwen Zhang, Yi-chieh Lee,
• Abstract summary: This study examines the effects of uncalibrated AI confidence on users' trust in AI, AI advice adoption, and collaboration outcomes. Deficiency of trust calibration support exacerbates this issue by making it harder to detect uncalibrated confidence. Our findings highlight the importance of AI confidence calibration for enhancing human-AI collaboration.
• Score: 5.480154202794587
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI transparency is a central pillar of responsible AI deployment and effective human-AI collaboration. A critical approach is communicating uncertainty, such as displaying AI's confidence level, or its correctness likelihood (CL), to users. However, these confidence levels are often uncalibrated, either overestimating or underestimating actual CL, posing risks and harms to human-AI collaboration. This study examines the effects of uncalibrated AI confidence on users' trust in AI, AI advice adoption, and collaboration outcomes. We further examined the impact of increased transparency, achieved through trust calibration support, on these outcomes. Our results reveal that uncalibrated AI confidence leads to both the misuse of overconfident AI and disuse of unconfident AI, thereby hindering outcomes of human-AI collaboration. Deficiency of trust calibration support exacerbates this issue by making it harder to detect uncalibrated confidence, promoting misuse and disuse of AI. Conversely, trust calibration support aids in recognizing uncalibration and reducing misuse, but it also fosters distrust and causes disuse of AI. Our findings highlight the importance of AI confidence calibration for enhancing human-AI collaboration and suggest directions for AI design and regulation.

Related papers

• The Impact and Feasibility of Self-Confidence Shaping for AI-Assisted Decision-Making [6.852960508141108]
  This paper presents an intervention for self-confidence shaping, designed to calibrate self-confidence at a targeted level. We show that self-confidence shaping can improve human-AI team performance by nearly 50% by mitigating both over- and under-reliance on AI. The observed relationship between sentiment and self-confidence suggests that modifying sentiment could be a viable strategy for shaping self-confidence.
  arXiv  Detail & Related papers  (2025-02-20T06:55:41Z)
• Human-Alignment Influences the Utility of AI-assisted Decision Making [16.732483972136418]
  We investigate what extent the degree of alignment actually influences the utility of AI-assisted decision making. Our results show a positive association between the degree of alignment and the utility of AI-assisted decision making.
  arXiv  Detail & Related papers  (2025-01-23T19:01:47Z)
• As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making [37.192236418976265]
  In human-AI decision-making, users' self-confidence aligns with AI confidence and such alignment can persist even after AI ceases to be involved. The presence of real-time correctness feedback of decisions reduced the degree of alignment.
  arXiv  Detail & Related papers  (2025-01-22T13:25:14Z)
• Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimization [53.80919781981027]
  Key requirements for trustworthy AI can be translated into design choices for the components of empirical risk minimization. We hope to provide actionable guidance for building AI systems that meet emerging standards for trustworthiness of AI.
  arXiv  Detail & Related papers  (2024-10-25T07:53:32Z)
• A Diachronic Perspective on User Trust in AI under Uncertainty [52.44939679369428]
  Modern NLP systems are often uncalibrated, resulting in confidently incorrect predictions that undermine user trust. We study the evolution of user trust in response to trust-eroding events using a betting game.
  arXiv  Detail & Related papers  (2023-10-20T14:41:46Z)
• Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making [36.50604819969994]
  In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. We modeled humans' CL by approximating their decision-making models and computing their potential performance in similar instances. We proposed three CL exploitation strategies to calibrate users' trust explicitly/implicitly in the AI-assisted decision-making process.
  arXiv  Detail & Related papers  (2023-01-14T02:51:01Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• Trustworthy AI: A Computational Perspective [54.80482955088197]
  We focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.
  arXiv  Detail & Related papers  (2021-07-12T14:21:46Z)
• Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI [55.4046755826066]
  We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i.e., trust between people) We incorporate a formalization of 'contractual trust', such that trust between a user and an AI is trust that some implicit or explicit contract will hold. We discuss how to design trustworthy AI, how to evaluate whether trust has manifested, and whether it is warranted.
  arXiv  Detail & Related papers  (2020-10-15T03:07:23Z)
• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making [53.62514158534574]
  We study whether features that reveal case-specific model information can calibrate trust and improve the joint performance of the human and AI. We show that confidence score can help calibrate people's trust in an AI model, but trust calibration alone is not sufficient to improve AI-assisted decision making.
  arXiv  Detail & Related papers  (2020-01-07T15:33:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.