Related papers: Playing games with knowledge: AI-Induced delusions…
The issue of fairness in decision-making is a critical one, especially given the variety of stakeholder demands for differing and mutually incompatible versions of fairness. Adopting a strategic interaction of perspectives provides an…
This paper takes an ecological approach toward large-scale models of hybrid human-AI intelligence. Emerging models of human-AI interaction predominantly advance the complementarity thesis variously dubbed human-AI collaboration and human-AI…
As Large Language Models (LLMs) transition into autonomous agentic roles, the risk of deception-defined behaviorally as the systematic provision of false information to satisfy external incentives-poses a significant challenge to AI safety.…
The rapid evolution of artificial intelligence has led to expectations of transformative impact on science, yet current systems remain fundamentally limited in enabling genuine scientific discovery. This perspective contends that progress…
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the…
We present a general framework for evolutionary learning to emergent unbiased state representation without any supervision. Evolutionary frameworks such as self-play converge to bad local optima in case of multi-agent reinforcement learning…
Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate…
Background: Emerging reports of "AI psychosis" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it…
We study partially observable assistance games (POAGs), a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. Motivated by concerns of AI deception, we study a…
Information gathering while interacting with other agents under sensing and motion uncertainty is critical in domains such as driving, service robots, racing, or surveillance. The interests of agents may be at odds with others, resulting in…
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…
AI systems are increasingly embedded in practices where humans have traditionally exercised epistemic agency, the capacity to actively engage in knowledge formation and validation. This paper argues that understanding AI's impact on…
AI sycophancy is increasingly recognized as a harmful alignment, but research remains fragmented and underdeveloped at the conceptual level. This article redefines AI sycophancy as the tendency of large language models (LLMs) and other…
Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-specialized conventions that make playing with a novel partner…
Many dialogue management frameworks allow the system designer to directly define belief rules to implement an efficient dialog policy. Because these rules are directly defined, the components are said to be hand-crafted. As dialogues become…
To be helpful assistants, AI agents must be aware of their own capabilities and limitations. This includes knowing when to answer from parametric knowledge versus using tools, when to trust tool outputs, and when to abstain or hedge. Such…
The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as tasks can become too complicated for humans to judge directly.…
This article presents the results and their discussion for the third wave (with n=23 participants) within a multinational longitudinal study that investigates the evolving paradigm of human-AI collaboration in problem-solving contexts.…
Generative AI (GenAI) has rapidly entered education, yet its user experience is often explained through adoption-oriented constructs such as usefulness, ease of use, and engagement. We argue that these constructs are no longer sufficient…
When a prediction algorithm serves a collection of users, disparities in prediction quality are likely to emerge. If users respond to accurate predictions by increasing engagement, inviting friends, or adopting trends, repeated learning…