Related papers: Privileged Self-Access Matters for Introspection i…
We tackle the question of whether an agent can, by suitable choice of prompts, control an AI bot to any state. To that end, we first introduce a formal definition of ``meaning'' that is amenable to analysis. Then, we characterize…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
Language models (LM or LLM) are increasingly deployed in the field of artificial intelligence (AI) and its applications, but the question arises as to whether they can be a common resource managed and maintained by a community of users.…
This study examines the understudied role of algorithmic evaluation of human judgment in hybrid decision-making systems, a critical gap in management research. While extant literature focuses on human reluctance to follow algorithmic…
In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of…
AI has surpassed humans across a variety of tasks such as image classification, playing games (e.g., go, "Starcraft" and poker), and protein structure prediction. However, at the same time, AI is also bearing serious controversies. Many…
Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many…
The imposing evolution of artificial intelligence systems and, specifically, of Large Language Models (LLM) makes it necessary to carry out assessments of their level of risk and the impact they may have in the area of privacy, personal…
This study proposes an approach to describing personality dynamics through mathematical modelling of introversion, extroversion, and ambiversion processes. Introversion is interpreted as a recursive process characterized by deep…
The need for explanations in AI has, by and large, been driven by the desire to increase the transparency of black-box machine learning models. However, such explanations, which focus on the internal mechanisms that lead to a specific…
This paper discusses the limitations of machine learning (ML), particularly deep artificial neural networks (ANNs), which are effective at approximating complex functions but often lack transparency and explanatory power. It highlights the…
AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and…
As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving…
Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…
Concerns around future dangers from advanced AI often centre on systems hypothesised to have intrinsic characteristics such as agent-like behaviour, strategic awareness, and long-range planning. We label this cluster of characteristics as…
LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability. In this research track, we propose the Chain-of-Embedding (CoE) in the latent space to enable LLMs…
Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…
Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models…
The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel…
The integration of slow-thinking mechanisms into large language models (LLMs) offers a promising way toward achieving Level 2 AGI Reasoners, as exemplified by systems like OpenAI's o1. However, several significant challenges remain,…