相关论文: Invisible failures in human-AI interactions

As AI systems become more advanced, concerns about large-scale risks from misuse or accidents have grown. This report analyzes the technical research into safe AI development being conducted by three leading AI companies: Anthropic, Google…

As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents - harm events to individuals and society. As a result, industry, civil society, and governments…

AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify,…

Artificial Intelligence (AI) systems are frequently employed in online services to provide personalized experiences to users based on large collections of data. However, AI systems can be designed in different ways, with black-box AI…

Despite significant advancements in AI-driven educational systems and ongoing calls for responsible AI for education, several critical issues remain unresolved -- acting as the elephant in the room within AI in education, learning…

Artificial Intelligence (AI) systems introduce unprecedented privacy challenges as they process increasingly sensitive data. Traditional privacy frameworks prove inadequate for AI technologies due to unique characteristics such as…

Large Language Models have become an integral part of new intelligent and interactive writing assistants. Many are offered commercially with a chatbot-like UI, such as ChatGPT, and provide little information about their inner workings. This…

When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content…

Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned…

Motivations: Recent research has emerged on generally how to improve AI product user experiences, but relatively little is known about an AI product's inclusivity. For example, what kinds of users does it support well, and who does it leave…

When large language models (LLMs) are consulted as forecasting tools, the independence of individual errors -- the foundation of collective intelligence -- may collapse. We test three conditions necessary for this "epistemic monoculture" to…

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…

Trust is widely regarded as a critical component to building artificial intelligence (AI) systems that people will use and safely rely upon. As research in this area continues to evolve, it becomes imperative that the research community…

Given the rapid advancement of large-scale language models, artificial intelligence (AI) models, like ChatGPT, are playing an increasingly prominent role in human society. However, to ensure that artificial intelligence models benefit human…

As artificial intelligence (AI) becomes integral to economy and society, communication gaps between developers, users, and stakeholders hinder trust and informed decision-making. High-level AI labels, inspired by frameworks like EU energy…

What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on…

Large language models (LLMs) can provide users with false, inaccurate, or misleading information, and we consider the output of this type of information as what Natale (2021) calls `banal' deceptive behaviour. Here, we investigate peoples'…

As AI code assistants become increasingly integrated into software development workflows, understanding how their code compares to human-written programs is critical for ensuring reliability, maintainability, and security. In this paper, we…

The rise of AI voice-cloning technology, particularly audio Real-time Deepfakes (RTDFs), has intensified social engineering attacks by enabling real-time voice impersonation that bypasses conventional enrollment-based authentication. This…

AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving productivity. We pursue mechanisms for leveraging signals about…