47 citations · 60 across the 34 of their papers we have counts for
36 papers
ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
Olivia Macmillan-Scott, Mirco Musolesi
Values such as honesty, autonomy, and confidentiality are often regarded as general principles underpinning AI alignment. However, what it means to act in accordance with these val…
Framing the Narrative: Ideological Mimicry in Large Language Models
Olivia Macmillan-Scott, Michael Jacobs, Nils Metternich +1
Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's stance as a relatively stable…
The relationship between professional and general ethics in generative AI
Omri Asscher, Mirco Musolesi
Recent years have seen a growing discrepancy in the field of AI alignment: research and policy recommendations on AI ethics tend to assume a general set of ethical values, yet prol…
The Role of Network Topology and Opponent Information in Shaping Cooperation in Multi-Agent Reinforcement Learning Systems
Seongho Son, Stephen Hailes, Mirco Musolesi
Several works have investigated the influence of graph topology on cooperation among artificial agents, while the majority of the literature has focused on modelling agents' adapta…
The Limits of Automatic Evaluation of Creativity in Large Language Models
Alessandro Tutone, Giorgio Franceschelli, Mirco Musolesi
Large Language Models (LLMs) are increasingly capable of generating text that challenges human performance in domains requiring creativity, yet evaluating creativity in LLM-generat…
On Distributional Reinforcement Learning in Chaotic Dynamical Systems
James Rudd-Jones, Mirco Musolesi, María Pérez-Ortiz
Chaotic dynamical systems pose a fundamental challenge for Reinforcement Learning (RL): exponential sensitivity to initial conditions induces high-variance bootstrap targets and po…
Emergent Semantic Role Understanding in Language Models
Carla Griffiths, Mirco Musolesi
Understanding how linguistic structure emerges in language models is central to interpreting what these systems learn from data and how much supervision they truly require. In part…
On the Creativity of AI Agents
Giorgio Franceschelli, Mirco Musolesi
Large language models (LLMs), particularly when integrated into agentic systems, have demonstrated human- and even superhuman-level performance across multiple domains. Whether the…
MarcoPolo: A Zero-Permission Attack for Location Type Inference from the Magnetic Field using Mobile Devices
Beatrice Perez, Abhinav Mehrotra, Mirco Musolesi
Location information extracted from mobile devices has been largely exploited to reveal our routines, significant places, and interests just to name a few. Given the sensitivity of…
An Agent-Centric Dynamical Systems Perspective on Multi-Agent Reinforcement Learning
James Rudd-Jones, María Pérez-Ortiz, Mirco Musolesi
Analysing learning in Multi-Agent Reinforcement Learning (MARL) environments is challenging, in particular with respect to \textit{individual} decision-making. Practitioners freque…
GenTract: Generative Global Tractography
Alec Sargood, Lemuel Puglisi, Elinor Thompson +2
Tractography is the process of inferring the trajectories of white-matter pathways in the brain from diffusion magnetic resonance imaging (dMRI). Local tractography methods, which…
Opponent Shaping in LLM Agents
Marta Emili Garcia Segura, Stephen Hailes, Mirco Musolesi
Large Language Models (LLMs) are increasingly being deployed as autonomous agents in real-world environments. As these deployments scale, multi-agent interactions become inevitable…
A Generalized Information Bottleneck Theory of Deep Learning
Charles Westphal, Stephen Hailes, Mirco Musolesi
The Information Bottleneck (IB) principle offers a compelling theoretical framework to understand how neural networks (NNs) learn. However, its practical utility has been constrain…
Complexity-Regularized Proximal Policy Optimization
Luca Serfilippi, Giorgio Franceschelli, Antonio Corradi +1
Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform di…
Reward Model Overoptimisation in Iterated RLHF
Lorenz Wolf, Robert Kirk, Mirco Musolesi
Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model o…
Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis
James Rudd-Jones, Mirco Musolesi, María Pérez-Ortiz
Climate policy development faces significant challenges due to deep uncertainty, complex system dynamics, and competing stakeholder interests. Climate simulation methods, such as E…
Quantum Chemistry Driven Molecular Inverse Design with Data-free Reinforcement Learning
Francesco Calcagno, Luca Serfilippi, Giorgio Franceschelli +3
The inverse design of molecules has challenged chemists for decades. In the past years, machine learning and artificial intelligence have emerged as new tools to generate molecules…
DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation
Giorgio Franceschelli, Mirco Musolesi
Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and…
Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation
Giorgio Franceschelli, Mirco Musolesi
Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling at higher temperatures, can compromis…
Feature Selection for Network Intrusion Detection
Charles Westphal, Stephen Hailes, Mirco Musolesi
Network Intrusion Detection (NID) remains a key area of research within the information security community, while also being relevant to Machine Learning (ML) practitioners. The la…
Mutual Information Preserving Neural Network Pruning
Charles Westphal, Stephen Hailes, Mirco Musolesi
Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers…
Moral Alignment for LLM Agents
Elizaveta Tennant, Stephen Hailes, Mirco Musolesi
Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are curr…
Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies
Alexei Pisacane, Victor-Alexandru Darvariu, Mirco Musolesi
Graph path search is a classic computer science problem that has been recently approached with Reinforcement Learning (RL) due to its potential to outperform prior methods. Existin…
Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law
Giorgio Franceschelli, Claudia Cevenini, Mirco Musolesi
The training process of foundation models as for other classes of deep learning systems is based on minimizing the reconstruction error over a training set. For this reason, they a…