77 citations · 126 across the 16 of their papers we have counts for
7 papers · 1 filter
RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection
Elia Onofri, Roberto Di Pietro
Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary frontier models, costly and ill-s…
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…
I-(OT)^2: A Client-optimal Oblivious Transfer Protocol for IoT Devices
Elia Onofri, Andrea Ciccotelli, Roberto Di Pietro
Oblivious Transfer (OT) is a fundamental cryptographic primitive enabling privacy-preserving computation and constitutes a core building block for secure multi-party computation wh…
COD-ssi: Enforcing Mutual Privacy for Credential Oblivious Disclosure in Self Sovereign Identity
Elia Onofri, Andrea De Salve, Paolo Mori +2
The Self-Sovereign Identity (SSI) paradigm is instrumental for decentralised identity management, allowing an entity to create, manage, and present their digital credentials withou…
Bayesian methods for the identification of model parameters for water transport in porous media
Paola Stolfi, Elia Onofri, Gabriella Bretti
The structure of the nonlinear inverse problem arising from capillarity-driven imbibition in porous media is investigated, considering a degenerate parabolic PDE with compactly sup…
Structural Identifiability and Comparative Calibration of Water Retention Curves for Imbibition in Porous Media
Gabriella Bretti, Maurizio Ceseri, Elia Onofri +1
This paper investigates the structural identifiability and a comparative calibration of four water retention curves (WRCs) within the framework of the Richards equation coupled wit…
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…