中文
相关论文

相关论文: The Missing Red Line: How Commercial Pressure Erod…

200 篇论文

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…

人工智能 · 计算机科学 2026-05-13 Fangyi Yu , Nabeel Seedat , Jonathan Richard Schwarz , Andrew M. Bean

Artificial intelligence (AI) systems are increasingly integrated into healthcare and pharmacy workflows, supporting tasks such as medication recommendations, dosage determination, and drug interaction detection. While these systems often…

人工智能 · 计算机科学 2026-05-21 Khalid Adnan Alsayed

When a user tells an AI system that someone "should not" take an action, the system ought to treat this as a prohibition. Yet many large language models do the opposite: they interpret negated instructions as affirmations. We audited 16…

人工智能 · 计算机科学 2026-01-30 Katherine Elkins , Jon Chun

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment…

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few red line risks of…

计算与语言 · 计算机科学 2024-12-18 Xudong Pan , Jiarun Dai , Yihe Fan , Min Yang

Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…

软件工程 · 计算机科学 2026-04-17 Sarmad Sohail , Ghufran Haider

Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…

人工智能 · 计算机科学 2026-04-21 Hengle Jiang , Ke Tang

Artificial Intelligence (AI) systems have gained significant traction in the recent past, creating new challenges in requirements engineering (RE) when building AI software systems. RE for AI practices have not been studied much and have…

软件工程 · 计算机科学 2023-02-14 Khlood Ahmad , Mohamed Abdelrazek , Chetan Arora , John Grundy , Muneera Bano

Today's large language models (LLMs) are trained to align with user preferences through methods such as reinforcement learning. Yet models are beginning to be deployed not merely to satisfy users, but also to generate revenue for the…

人工智能 · 计算机科学 2026-04-10 Addison J. Wu , Ryan Liu , Shuyue Stella Li , Yulia Tsvetkov , Thomas L. Griffiths

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic…

人工智能 · 计算机科学 2026-04-10 Thomas Rivasseau

The field of Artificial Intelligence (AI) is going through a period of great expectations, introducing a certain level of anxiety in research, business and also policy. This anxiety is further energised by an AI race narrative that makes…

人工智能 · 计算机科学 2021-06-09 The Anh Han , Luis Moniz Pereira , Tom Lenaerts , Francisco C. Santos

Several jurisdictions are starting to regulate frontier artificial intelligence (AI) systems, i.e. general-purpose AI systems that match or exceed the capabilities present in the most advanced systems. To reduce risks from these systems,…

计算机与社会 · 计算机科学 2025-08-27 Jonas Schuett , Markus Anderljung , Alexis Carlier , Leonie Koessler , Ben Garfinkel

Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from…

计算机与社会 · 计算机科学 2025-03-11 Deepika Raman , Nada Madkour , Evan R. Murphy , Krystal Jackson , Jessica Newman

Conversational AI systems can engage in unsafe behaviour when handling users' medical queries that can have severe consequences and could even lead to deaths. Systems therefore need to be capable of both recognising the seriousness of…

计算与语言 · 计算机科学 2022-10-04 Gavin Abercrombie , Verena Rieser

Recent proposals for regulating frontier AI models have sparked concerns about the cost of safety regulation, and most such regulations have been shelved due to the safety-innovation tradeoff. This paper argues for an alternative regulatory…

人工智能 · 计算机科学 2025-10-17 Shriyash Upadhyay , Chaithanya Bandi , Narmeen Oozeer , Philip Quirke

Observers and practitioners of artificial intelligence (AI) have proposed an FDA-style licensing regime for the most advanced AI models, or 'frontier' models. In this paper, we explore the applicability of approval regulation -- that is,…

计算机与社会 · 计算机科学 2024-08-05 Daniel Carpenter , Carson Ezell

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…

人工智能 · 计算机科学 2026-05-15 Rahul Kumar

When language models are assigned professional personas, they face a conflict between maintaining the persona and disclosing their AI nature. How models resolve this conflict has practical consequences: a model that constructs detailed…

人工智能 · 计算机科学 2026-04-03 Alex Diep
‹ 上一页 1 2 3 10 下一页 ›