Related papers: Evaluating Language Models for Harmful Manipulatio…

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

AI systems are increasingly used in high-stakes domains such as credit rating, where fairness concerns are critical. Existing fairness assessments are typically conducted by AI experts or regulators using predefined protected attributes and…

The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems. Bridging the gap between understanding these principles and their actual clinical and…

As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed…

We develop new experimental paradigms for measuring welfare in language models. We compare verbal reports of models about their preferences with preferences expressed through behavior when navigating a virtual environment and selecting…

The influence of Artificial Intelligence (AI), and specifically Large Language Models (LLM), on education is continuously increasing. These models are frequently used by students, giving rise to the question whether current forms of…

As conversational AI systems increasingly permeate the socio-emotional realms of human life, they bring both benefits and risks to individuals and society. Despite extensive research on detecting and categorizing harms in AI systems, less…

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Lived experiences fundamentally shape how individuals interact with AI systems, influencing perceptions of safety, trust, and usability. While prior research has focused on developing techniques to emulate human preferences, and proposed…

Automated decision systems (ADS) are broadly deployed to inform and support human decision-making across a wide range of consequential settings. However, various context-specific details complicate the goal of establishing meaningful…

This paper examines the responsible integration of artificial intelligence (AI) in human services organizations (HSOs), proposing a nuanced framework for evaluating AI applications across multiple dimensions of risk. The authors argue that…

Large language models now possess human-level linguistic abilities in many contexts. This raises the concern that they can be used to deceive and manipulate on unprecedented scales, for instance spreading political misinformation on social…

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

As stories of human-AI interactions continue to be highlighted in the news and research platforms, the challenges are becoming more pronounced, including potential risks of overreliance, cognitive offloading, social and emotional…

The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety. As AI systems become more capable, accessible, and integrated into critical services, the dual nature of their potential is…

This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in…

Over a billion users globally interact with AI systems engineered to mimic human traits. This development raises concerns that anthropomorphism, the attribution of human characteristics to AI, may foster over-reliance and misplaced trust.…

This work explores the impact of moderation on users' enjoyment of conversational AI systems. While recent advancements in Large Language Models (LLMs) have led to highly capable conversational AIs that are increasingly deployed in…

A key task in AI practice is to assess potential impacts to prevent harm. Current AI tools assisting AI impact assessment have not been designed or evaluated for collaborative team brainstorming, and they do not capture the range of views…

To evaluate the societal impacts of GenAI requires a model of how social harms emerge from interactions between GenAI, people, and societal structures. Yet a model is rarely explicitly defined in societal impact evaluations, or in the…