Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

Placing a human in the loop may help abate the risks of deploying AI systems in safety-
critical settings (eg, a clinician working with a medical AI system). However, mitigating risks …

Recently, learning with soft labels has been shown to achieve better performance than
learning with hard labels in terms of model generalization, calibration, and robustness …

When groups of people are tasked with making a judgment, the issue of uncertainty often
arises. Existing methods to reduce uncertainty typically focus on iteratively improving …

Supervised learning typically focuses on learning transferable representations from training
examples annotated by humans. While rich annotations (like soft labels) carry more …

Contemporary vision benchmarks predominantly consider tasks on which humans can
achieve near-perfect performance. However, humans are frequently presented with visual …

With the rise of increasingly powerful and user-facing NLP systems, there is growing interest
in assessing whether they have a good representation of uncertainty by evaluating the …

In this paper, we address the concept of" alignment" in large language models (LLMs)
through the lens of post-structuralist socio-political theory, specifically examining its parallels …

Individual human decision-makers may benefit from different forms of support to improve
decision outcomes. However, a key question is which form of support will lead to accurate …

Human-annotated data plays a critical role in the fairness of AI systems, including those that
deal with life-altering decisions or moderating human-created web/social media content …