相关论文: The Hot Mess of AI: How Does Misalignment Scale Wi…

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…

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…

An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce…

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…

Artificial intelligence (AI) models for computer vision trained with supervised machine learning are assumed to solve classification tasks by imitating human behavior learned from training labels. Most efforts in recent vision research…

Optimizing a given metric is a central aspect of most current AI approaches, yet overemphasizing metrics leads to manipulation, gaming, a myopic focus on short-term goals, and other unexpected negative consequences. This poses a fundamental…

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…

Instances of Artificial Intelligence (AI) systems failing to deliver consistent, satisfactory performance are legion. We investigate why AI failures occur. We address only a narrow subset of the broader field of AI Safety. We focus on AI…

Rapidly increasing AI capabilities have substantial real-world consequences, ranging from AI safety concerns to labor market consequences. The Model Evaluation & Threat Research (METR) report argues that AI capabilities have exhibited…

The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence…

Shared mental models are critical to team success; however, in practice, team members may have misaligned models due to a variety of factors. In safety-critical domains (e.g., aviation, healthcare), lack of shared mental models can lead to…

The field of eXplainable artificial intelligence (XAI) has produced a plethora of methods (e.g., saliency-maps) to gain insight into artificial intelligence (AI) models, and has exploded with the rise of deep learning (DL). However,…

The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While…

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…

The past decade has seen incredible scaling of AI systems by a few companies, leading to inequality in AI model performance. This paper argues that, contrary to prevailing intuition, the diminishing returns to compute scaling will lead to a…

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these demands conflict reveals a principal hierarchy -- an implicit…