Related papers: Principles Do Not Apply Themselves: A Hermeneutic …

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…

It has recently been argued that AI models' representations are becoming aligned as their scale and performance increase. Empirical analyses have been designed to support this idea and conjecture the possible alignment of different…

Human-AI collaboration is increasingly relevant in consequential areas where AI recommendations support human discretion. However, human-AI teams' effectiveness, capability, and fairness highly depend on human perceptions of AI. Positive…

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…

Interactions with AI assistants are increasingly personalized to individual users. As AI personalization is dynamic and machine-learning-driven, we have limited understanding of how personalization affects interaction outcomes and user…

The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, the commitment to AI…

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Disagreements are widespread across the design, evaluation, and alignment pipelines of artificial intelligence (AI) systems. Yet, standard practices in AI development often obscure or eliminate disagreement, resulting in an engineered…

Assessing the trustworthiness of artificial intelligence systems requires knowledge from many different disciplines. These disciplines do not necessarily share concepts between them and might use words with different meanings, or even use…

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI…

When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which…

Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in…

Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of…

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematically study rationales…

Traditionally, the way one evaluates the performance of an Artificial Intelligence (AI) system is via a comparison to human performance in specific tasks, treating humans as a reference for high-level cognition. However, these comparisons…