相关论文: The Missing Red Line: How Commercial Pressure Erod…
If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…
Artificial intelligence's (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language…
Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…
Frontier AI labs face intense commercial competitive pressure to develop increasingly powerful systems, raising the risk of a race to the bottom on safety. Voluntary coordination among labs - including by way of joint safety testing,…
Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…
AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of…
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. Here, we show that…
The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. Motivated by such applications, this paper is dedicated to fundamental modeling…
Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…
In settings where users both need high accuracy and are time-pressured, such as doctors working in emergency rooms, we want to provide AI assistance that both increases decision accuracy and reduces decision-making time. Current literature…
The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure under legacy cyber, technology errors-and-omissions (E&O),…
People experiencing mental health crises frequently turn to open-ended generative AI (GenAI) chatbots for support. However, rather than providing immediate assistance, some GenAI chatbots are designed to respond to crisis situations in ways…
Existing legal frameworks on AI rely on training compute thresholds as a proxy to identify potentially-dangerous AI models and trigger increased regulatory attention. In the United States, Section 4.2(a) of Executive Order 14110 instructs…
Artificial Intelligence (AI) is rapidly being integrated into critical systems across various domains, from healthcare to autonomous vehicles. While its integration brings immense benefits, it also introduces significant risks, including…
The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats,…
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…
Advancements in Artificial Intelligence (AI) technologies' social fluency are being integrated into commercial interactions. As tools such as OpenAI's assistant are integrated into platforms such as Shopify, Klarna, and Visa, understanding…
Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…
The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch problem as a signalling game, where a human decision-maker…