Related papers: Uncalibrated Models Can Improve Human-AI Collabora…

Today, AI is being increasingly used to help human experts make decisions in high-stakes scenarios. In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts…

In AI-assisted decision-making, it is crucial but challenging for humans to achieve appropriate reliance on AI. This paper approaches this problem from a human-centered perspective, "human self-confidence calibration". We begin by proposing…

Providing well-calibrated AI confidence can help promote users' appropriate trust in and reliance on AI, which are essential for AI-assisted decision-making. However, calibrating AI confidence -- providing confidence score that accurately…

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…

Complementary collaboration between humans and AI is essential for human-AI decision making. One feasible approach to achieving it involves accounting for the calibrated confidence levels of both AI and users. However, this process would…

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…

Appropriate reliance is critical to achieving synergistic human-AI collaboration. For instance, when users over-rely on AI assistance, their human-AI team performance is bounded by the model's capability. This work studies how the…

AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge…

Productive human-AI collaboration requires appropriate reliance, yet contemporary AI systems are often miscalibrated, exhibiting systematic overconfidence or underconfidence. We investigate whether humans can learn to mentally recalibrate…

In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify their decision. With the increasing prevalence of such…

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…

Whenever a binary classifier is used to provide decision support, it typically provides both a label prediction and a confidence value. Then, the decision maker is supposed to use the confidence value to calibrate how much to trust the…

People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior…

When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A well-calibrated AI model is one that can reliably quantify…

In AI-assisted decision-making, it is crucial but challenging for humans to appropriately rely on AI, especially in high-stakes domains such as finance and healthcare. This paper addresses this problem from a human-centered perspective by…

Whenever an AI model is used to predict a relevant (binary) outcome in AI-assisted decision making, it is widely agreed that, together with each prediction, the model should provide an AI confidence value. However, it has been unclear why…

AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice. However, fully automating such high-stakes applications can raise ethical or fairness concerns. Instead, in such cases,…

In a human-AI collaboration, users build a mental model of the AI system based on its reliability and how it presents its decision, e.g. its presentation of system confidence and an explanation of the output. Modern NLP systems are often…

Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work,…

Joint human-AI inference holds immense potential to improve outcomes in human-supervised robot missions. Current day missions are generally in the AI-assisted setting, where the human operator makes the final inference based on the AI…