Recent advances in AI models have increased the integration of AI-based decision aids into the human decision making process. To fully unlock the potential of AI-assisted decision making, researchers have computationally modeled how humans incorporate AI recommendations into their final decisions, and utilized these models to improve human-AI team performance. Meanwhile, due to the ``black-box'' nature of AI models, providing AI explanations to human decision makers to help them rely on AI recommendations more appropriately has become a common practice. In this paper, we explore whether we can quantitatively model how humans integrate both AI recommendations and explanations into their decision process, and whether this quantitative understanding of human behavior from the learned model can be utilized to manipulate AI explanations, thereby nudging individuals towards making targeted decisions. Our extensive human experiments across various tasks demonstrate that human behavior can be easily influenced by these manipulated explanations towards targeted outcomes, regardless of the intent being adversarial or benign. Furthermore, individuals often fail to detect any anomalies in these explanations, despite their decisions being affected by them.

Concerns about how workers are perceived can deter effective collaboration with artificial intelligence (AI). In a field experiment on a large online labor market, I hired 450 U.S.-based remote workers to complete an image-categorization job assisted by AI recommendations. Workers were incentivized by the prospect of a contract extension based on an HR evaluator's feedback. I find that workers adopt AI recommendations at lower rates when their reliance on AI is visible to the evaluator, resulting in a measurable decline in task performance. The effects are present despite a conservative design in which workers know that the evaluator is explicitly instructed to assess expected accuracy on the same AI-assisted task. This reduction in AI reliance persists even when the evaluator is reassured about workers' strong performance history on the platform, underscoring how difficult these concerns are to alleviate. Leveraging the platform's public feedback feature, I introduce a novel incentive-compatible elicitation method showing that workers fear heavy reliance on AI signals a lack of confidence in their own judgment, a trait they view as essential when collaborating with AI.

For example, V odrahalli, Gerstenberg, and Zou [6] developed a human behavior model to characterize the impact of AI predictions and confidence levels on human final decisions.

In this study, we conduct a resume-screening experiment (N=528) where people collaborate with simulated AI models exhibiting race-based preferences (bias) to evaluate candidates for 16 high and low status occupations. Simulated AI bias approximates factual and counterfactual estimates of racial bias in real-world AI systems. We investigate people's preferences for White, Black, Hispanic, and Asian candidates (represented through names and affinity groups on quality-controlled resumes) across 1,526 scenarios and measure their unconscious associations between race and status using implicit association tests (IATs), which predict discriminatory hiring decisions but have not been investigated in human-AI collaboration. When making decisions without AI or with AI that exhibits no race-based preferences, people select all candidates at equal rates. However, when interacting with AI favoring a particular group, people also favor those candidates up to 90% of the time, indicating a significant behavioral shift. The likelihood of selecting candidates whose identities do not align with common race-status stereotypes can increase by 13% if people complete an IAT before conducting resume screening. Finally, even if people think AI recommendations are low quality or not important, their decisions are still vulnerable to AI bias under certain circumstances. This work has implications for people's autonomy in AI-HITL scenarios, AI and work, design and evaluation of AI hiring systems, and strategies for mitigating bias in collaborative decision-making tasks. In particular, organizational and regulatory policy should acknowledge the complex nature of AI-HITL decision making when implementing these systems, educating people who use them, and determining which are subject to oversight.

Social media platforms today strive to improve user experience through AI recommendations, yet the value of such recommendations vanishes as users do not understand the reasons behind them. This issue arises becaus e explainability in social media is general and lacks alignment with user - specific needs. In this vision paper, we outline a user - segmented and context - aware explanation layer by proposing a visual explanation system with diverse explanation methods. The p roposed system is framed by the variety of user needs and contexts, showing explanations in different visualized forms, including a technically detailed version for AI experts and a simplified one for lay users. Our framework is the first to jointly adapt explanation style (visual vs. numeric) and granularity (expert vs. lay) inside a single pipeline.

The increasing availability and use of artificial intelligence (AI) tools in educational settings has raised concerns about students' overreliance on these technologies. Overreliance occurs when individuals accept incorrect AI-generated recommendations, often without critical evaluation, leading to flawed problem solutions and undermining learning outcomes. This study investigates potential factors contributing to patterns of AI reliance among undergraduate students, examining not only overreliance but also appropriate reliance (correctly accepting helpful and rejecting harmful recommendations) and underreliance (incorrectly rejecting helpful recommendations). Our approach combined pre- and post-surveys with a controlled experimental task where participants solved programming problems with an AI assistant that provided both accurate and deliberately incorrect suggestions, allowing direct observation of students' reliance patterns when faced with varying AI reliability. We find that appropriate reliance is significantly related to students' programming self-efficacy, programming literacy, and need for cognition, while showing negative correlations with post-task trust and satisfaction. Overreliance showed significant correlations with post-task trust and satisfaction with the AI assistant. Underreliance was negatively correlated with programming literacy, programming self-efficacy, and need for cognition. Overall, the findings provide insights for developing targeted interventions that promote appropriate reliance on AI tools, with implications for the integration of AI in curriculum and educational technologies.

We are witnessing a surge in the use of artificial intelligence (AI) systems across various work environments, a trend likely to intensify in the coming years. As algorithmic predictive capabilities advance and digitization and data collection efforts expand, new opportunities are emerging to observe how professionals make decisions with the assistance of these tools. Machine learning algorithms are eclipsing experts in many areas, including bail judges predicting pretrial misconduct (Kleinberg et al. 2018), radiologists predicting pneumonia from chest X-rays (Rajpurkar et al. 2017; Topol 2019), and workforce professionals predicting productivity for hiring and promotion (Chalfin et al. 2016). While AI has the potential to outperform many human professionals, there is hope that human-AI collaboration can yield even better results by leveraging the unique strengths of each. AI excels at processing large volumes of data and remains free from emotional biases, while humans may possess private information or be better equipped to handle edge cases. One of the most popular decision-making frameworks involves humans making choices based on AI recommendations, a structure that preserves decision-making authority in human hands.

Recent advances in AI models have increased the integration of AI-based decision aids into the human decision making process. To fully unlock the potential of AI-assisted decision making, researchers have computationally modeled how humans incorporate AI recommendations into their final decisions, and utilized these models to improve human-AI team performance. Meanwhile, due to the black-box'' nature of AI models, providing AI explanations to human decision makers to help them rely on AI recommendations more appropriately has become a common practice. In this paper, we explore whether we can quantitatively model how humans integrate both AI recommendations and explanations into their decision process, and whether this quantitative understanding of human behavior from the learned model can be utilized to manipulate AI explanations, thereby nudging individuals towards making targeted decisions. Our extensive human experiments across various tasks demonstrate that human behavior can be easily influenced by these manipulated explanations towards targeted outcomes, regardless of the intent being adversarial or benign.

Decisions to deploy AI capabilities are often driven by counterfactuals - a comparison of decisions made using AI to decisions that would have been made if the AI were not used. Counterfactual misses, which are poor decisions that are attributable to using AI, may have disproportionate disutility to AI deployment decision makers. Counterfactual hits, which are good decisions attributable to AI usage, may provide little benefit beyond the benefit of better decisions. This paper explores how to include counterfactual outcomes into usage decision expected utility assessments. Several properties emerge when counterfactuals are explicitly included. First, there are many contexts where the expected utility of AI usage is positive for intended beneficiaries and strongly negative for stakeholders and deployment decision makers. Second, high levels of complementarity, where differing AI and user assessments are merged beneficially, often leads to substantial disutility for stakeholders. Third, apparently small changes in how users interact with an AI capability can substantially impact stakeholder utility. Fourth, cognitive biases such as expert overconfidence and hindsight bias exacerbate the perceived frequency of costly counterfactual misses. The expected utility assessment approach presented here is intended to help AI developers and deployment decision makers to navigate the subtle but substantial impact of counterfactuals so as to better ensure that beneficial AI capabilities are used.