4 papers
Consensus and Factual Dynamics in Large Populations of Interacting Language Models
Emanuele Ricco, Elia Onofri, Vincenzo Sammartino +1
Large Language Model (LLM) agents are increasingly deployed as populations of interacting entities, in which consensus --agreement on a shared answer-- emerges as a collective, une…
A Geometric Analysis of Small-sized Language Model Hallucinations
Emanuele Ricco, Elia Onofri, Lorenzo Cima +2
Hallucinations -- plausible but factually incorrect responses -- pose a major challenge to the reliability of Large Language Models (LLMs), especially in multi-step or agentic sett…
PRISM: Phase-enhanced Radial-based Image Signature Mapping framework for fingerprinting AI-generated images
Emanuele Ricco, Elia Onofri, Lorenzo Cima +2
A critical need has emerged for generative AI: attribution methods. That is, solutions that can identify the model originating AI-generated content. This feature, generally relevan…
Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis
Emanuele Ricco, Lorenzo Cima, Roberto Di Pietro
Hallucinations are one of the major issues affecting LLMs, hindering their wide adoption in production systems. While current research solutions for detecting hallucinations are ma…