Related papers: Scalable AI Safety via Doubly-Efficient Debate
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…
Recent advances in machine learning, particularly the emergence of foundation models, are leading to new opportunities to develop technology-based solutions to societal problems. However, the reasoning and inner workings of today's complex…
The United States Department of Defense (DOD) looks to accelerate the development and deployment of AI capabilities across a wide spectrum of defense applications to maintain strategic advantages. However, many common features of AI…
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…
AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…
Across academia, industry, and government, ``AI'' has become central in research and development, regulatory debates, and promises of ever faster and more capable decision-making and action. In numerous domains, especially safety-critical…
Developing and implementing AI-based solutions help state and federal government agencies, research institutions, and commercial companies enhance decision-making processes, automate chain operations, and reduce the consumption of natural…
Artificial intelligence (AI) can potentially transform global health, but algorithmic bias can exacerbate social inequities and disparity. Trustworthy AI entails the intentional design to ensure equity and mitigate potential biases. To…
Recently, a lot of attention has been given to undesired consequences of Artificial Intelligence (AI), such as unfair bias leading to discrimination, or the lack of explanations of the results of AI systems. There are several important…
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear that AI and business models based on it can only reach…
In the last few years, AI continues demonstrating its positive impact on society while sometimes with ethically questionable consequences. Building and maintaining public trust in AI has been identified as the key to successful and…
Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation…
Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate…
Artificial Intelligence (AI) has emerged as a transformative technology with the potential to revolutionize various sectors, from healthcare to finance, education, and beyond. However, successfully implementing AI systems remains a complex…
This study critically examines the commonly held assumption that explicability in artificial intelligence (AI) systems inherently boosts user trust. Utilizing a meta-analytical approach, we conducted a comprehensive examination of the…
Use of artificial intelligence (AI) in human contexts calls for ethical considerations for the design and development of AI-based systems. However, little knowledge currently exists on how to provide useful and tangible tools that could…
Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed…
This study proposes an "AI Development Support" approach that, unlike conventional AI Alignment-which aims to forcefully inject human values-supports the ethical and moral development of AI itself. As demonstrated by the Orthogonality…
Digital deliberation has expanded democratic participation, yet challenges remain. This includes processing information at scale, moderating discussions, fact-checking, or attracting people to participate. Recent advances in artificial…
Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…