Imperfections of XAI: phenomena influencing AI-assisted decision-making
Abstract
With the increasing use of AI, recent research in human–computer interaction explores Explainable AI (XAI) to make AI advice more interpretable. While research addresses the effects of incorrect AI advice on AI-assisted decision-making, the impact of incorrect explanations is neglected so far. Additionally, recent work shows that not only different explanation modalities impact decision-makers, but also human factors play a critical role. To analyze relevant phenomena influencing AI-assisted decision-making, this work explores the impacting factors by conceptualizing theories of appropriate reliance and taking the first steps toward empirical evidence. We show that humans’ reliance on AI and the human–AI team performance are impacted by imperfect XAI in a study with 136 participants. Additionally, we find that cognitive styles affect decision-making in different explanation modalities. Hence, we shed light on diverse factors that impact human–AI collaboration and provide guidelines for designers to tailor such human–AI collaboration systems to individuals’ needs.
Study specs
The researchers conducted a study with 136 participants, analyzing the effects of explanation imperfections and cognitive styles on AI-assisted decision-making and human–AI collaboration.
- Authors
- P Spitzer,K Morrison,V Turri,M Feng,A Perer
- Discipline
- Artificial Intelligence
- Sample Size
- N=136
- Study Type
- Experimental Study
- Year
- 2025
- Human Data Platform
- Prolific
- Source
- View Source Google Scholar
Measured Outcomes
The impact of incorrect explanations and explanation modalities on human reliance, decision-making, and human–AI team performance, as well as the role of cognitive styles.
Peer Review & Critical Discussion
Potential Selection Bias in 2023 Cohort
The participant pool shows a concerning overrepresentation of users from high-income demographics. Looking at Table 3, we can see that 78% of respondents had annual incomes above $75k, which significantly limits the generalizability of these findings to broader populations.
Non-naive Participants Issue
I've noticed a methodological concern regarding participant naivety. Given that Prolific users often complete multiple studies, there's a real risk that participants had prior exposure to similar experimental paradigms, which could confound the results.
RLHF Applicability to This Study Design
The implications for RLHF training pipelines are understated. If we accept the authors' conclusions about preference stability, this has direct consequences for how we should structure reward model training. The temporal decay effect described in Section 4.2 is particularly relevant.
Verify your expertise to join discussion
Create an account and verify your credentials to participate in peer discussions.