The Impact of Imperfect XAI on Human-AI Decision-Making
- URL: http://arxiv.org/abs/2307.13566v4
- Date: Wed, 8 May 2024 17:14:25 GMT
- Title: The Impact of Imperfect XAI on Human-AI Decision-Making
- Authors: Katelyn Morrison, Philipp Spitzer, Violet Turri, Michelle Feng, Niklas Kühl, Adam Perer,
- Abstract summary: We evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task.
Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance.
- Score: 8.305869611846775
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility of the explanations being incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task, taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems.
Related papers
- Raising the Stakes: Performance Pressure Improves AI-Assisted Decision Making [57.53469908423318]
We show the effects of performance pressure on AI advice reliance when laypeople complete a common AI-assisted task.
We find that when the stakes are high, people use AI advice more appropriately than when stakes are lower, regardless of the presence of an AI explanation.
arXiv Detail & Related papers (2024-10-21T22:39:52Z) - Interactive Example-based Explanations to Improve Health Professionals' Onboarding with AI for Human-AI Collaborative Decision Making [2.964175945467257]
A growing research explores the usage of AI explanations on user's decision phases for human-AI collaborative decision-making.
Previous studies found the issues of overreliance on wrong' AI outputs.
We propose interactive example-based explanations to improve health professionals' offboarding with AI.
arXiv Detail & Related papers (2024-09-24T07:20:09Z) - Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration [11.824688232910193]
We run a study on AI-assisted decision-making in which humans were supported by XAI.
Our findings reveal a misinformation effect when incorrect explanations accompany correct AI advice.
This effect causes humans to infer flawed reasoning strategies, hindering task execution and demonstrating impaired procedural knowledge.
arXiv Detail & Related papers (2024-09-19T14:34:20Z) - Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks.
We show that the learned AI control system demonstrates robustness against adversarial tampering.
In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
arXiv Detail & Related papers (2024-07-03T15:38:57Z) - Improving Health Professionals' Onboarding with AI and XAI for Trustworthy Human-AI Collaborative Decision Making [3.2381492754749632]
We present the findings of semi-structured interviews with health professionals and students majoring in medicine and health.
For the interviews, we built upon human-AI interaction guidelines to create materials of an AI system for stroke rehabilitation assessment.
Our findings reveal that beyond presenting traditional performance metrics on AI, participants desired benchmark information.
arXiv Detail & Related papers (2024-05-26T04:30:17Z) - Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making [47.33241893184721]
In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole.
We propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making.
Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates.
arXiv Detail & Related papers (2024-03-25T14:34:06Z) - Beyond Recommender: An Exploratory Study of the Effects of Different AI
Roles in AI-Assisted Decision Making [48.179458030691286]
We examine three AI roles: Recommender, Analyzer, and Devil's Advocate.
Our results show each role's distinct strengths and limitations in task performance, reliance appropriateness, and user experience.
These insights offer valuable implications for designing AI assistants with adaptive functional roles according to different situations.
arXiv Detail & Related papers (2024-03-04T07:32:28Z) - Towards Effective Human-AI Decision-Making: The Role of Human Learning
in Appropriate Reliance on AI Advice [3.595471754135419]
We show the relationship between learning and appropriate reliance in an experiment with 100 participants.
This work provides fundamental concepts for analyzing reliance and derives implications for the effective design of human-AI decision-making.
arXiv Detail & Related papers (2023-10-03T14:51:53Z) - Advancing Human-AI Complementarity: The Impact of User Expertise and
Algorithmic Tuning on Joint Decision Making [10.890854857970488]
Many factors can impact success of Human-AI teams, including a user's domain expertise, mental models of an AI system, trust in recommendations, and more.
Our study examined user performance in a non-trivial blood vessel labeling task where participants indicated whether a given blood vessel was flowing or stalled.
Our results show that while recommendations from an AI-Assistant can aid user decision making, factors such as users' baseline performance relative to the AI and complementary tuning of AI error types significantly impact overall team performance.
arXiv Detail & Related papers (2022-08-16T21:39:58Z) - Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted
Decision-making [46.625616262738404]
We use knowledge from the field of cognitive science to account for cognitive biases in the human-AI collaborative decision-making setting.
We focus specifically on anchoring bias, a bias commonly encountered in human-AI collaboration.
arXiv Detail & Related papers (2020-10-15T22:25:41Z) - 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.