相关论文: Learning to Trust: How Humans Mentally Recalibrate…

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…

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 many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure…

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…

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…

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…

Trust and reliance are often treated as coupled constructs in human-AI interaction research, with the assumption that calibrating trust will lead to appropriate reliance. We challenge this assumption in educational contexts, where students…

Trust biases how users rely on AI recommendations in AI-assisted decision-making tasks, with low and high levels of trust resulting in increased under- and over-reliance, respectively. We propose that AI assistants should adapt their…

Human-AI collaboration outcomes depend strongly on human self-confidence calibration, which drives reliance or resistance toward AI's suggestions. This work presents two studies examining whether calibration of self-confidence before…

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…

It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…

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…

We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical…

Many hyper-personalized AI systems profile people's characteristics (e.g., personality traits) to provide personalized recommendations. These systems are increasingly used to facilitate interactions among people, such as providing teammate…

Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the loss function used for training. However, the meta-alignment…

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…

Understanding how humans revise their beliefs in light of new information is crucial for developing AI systems which can effectively model, and thus align with, human reasoning. While theoretical belief revision frameworks rely on a set of…

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…