8 papers
Metaphor Is Not All Attention Needs
Olga Sorokoletova, Francesco Giarrusso, Giacomo De Luca +6
Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Although post-training aims to mak…
Learning from Mistakes: Can LLM Self-Recover after Misalignment?
Olga E. Sorokoletova, Francesco Giarrusso, Vincenzo Suriani +1
Responsible AI initiatives place great emphasis on the safety of Large Language Model (LLM)-based systems. In particular, it has become standard practice to subject these models to…
Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani +1
Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across lang…
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
Marcantonio Bracale Syrnikov, Federico Pierucci, Marcello Galisai +6
Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level…
Institutional AI: A Governance Framework for Distributional AGI Safety
Federico Pierucci, Marcello Galisai, Marcantonio Syrnikov Bracale +6
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but m…
From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
Piercosma Bisconti, Marcello Galisai, Matteo Prandi +6
Safety mechanisms in LLMs remain vulnerable to attacks that reframe harmful requests through culturally coded structures. We introduce Adversarial Tales, a jailbreak technique that…