相关论文: Maia-2: A Unified Model for Human-AI Alignment in …

As AI systems demonstrate increasingly strong predictive performance, their adoption has grown in numerous domains. However, in high-stakes domains such as criminal justice and healthcare, full automation is often not desirable due to…

As general-purpose artificial intelligence (AI) systems become increasingly integrated with diverse human communities, cultural alignment has emerged as a crucial element in their deployment. Most existing approaches treat cultural…

Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how…

As Large Language Models (LLMs) grow in capability, do they develop self-awareness as an emergent behavior? And if so, can we measure it? We introduce the AI Self-Awareness Index (AISAI), a game-theoretic framework for measuring…

We introduce the idea of Centaur Programmer, based on the premise that a collaborative approach between humans and AI will be more effective than AI alone, as demonstrated in centaur chess tournaments where mixed teams of humans and AI beat…

Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively.…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…

If machine learning models were to achieve superhuman abilities at various reasoning or decision-making tasks, how would we go about evaluating such models, given that humans would necessarily be poor proxies for ground truth? In this…

The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around academic integrity, fairness, and learning quality. While institutional responses…

In high-stakes disaster scenarios, timely and informed decision-making is critical yet often challenged by uncertainty, dynamic environments, and limited resources. This paper presents a systematic review of Human-AI collaboration patterns…

Adaptive machines have the potential to assist or interfere with human behavior in a range of contexts, from cognitive decision-making to physical device assistance. Therefore it is critical to understand how machine learning algorithms can…

Nowadays, we delegate many of our decisions to Artificial Intelligence (AI) that acts either in solo or as a human companion in decisions made to support several sensitive domains, like healthcare, financial services and law enforcement. AI…

Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a…

Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We…

AI approaches are progressing besting humans at game-related tasks (e.g. chess). The next stage is expected to be Human-AI collaboration; however, the research on this subject has been mixed and is in need of additional data points. We add…

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…

Aligning AI systems with human values fundamentally relies on effective human feedback. While significant research has addressed training algorithms, the role of user interface is often overlooked and only treated as an implementation…

AI practitioners typically strive to develop the most accurate systems, making an implicit assumption that the AI system will function autonomously. However, in practice, AI systems often are used to provide advice to people in domains…