6 papers
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
Andrea Bacciu, Andrea Alfarano, Saab Mansour +2
Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale e…
Select, Label, Evaluate: Active Testing in NLP
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu +2
Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requ…
The Majority Vote Paradigm Shift: When Popular Meets Optimal
Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti +3
Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels g…
Renormalized Graph Representations for Node Classification
Francesco Caso, Giovanni Trappolini, Andrea Bacciu +2
Graph neural networks process information on graphs represented at a given resolution scale. We analyze the effect of using different coarse-grained graph resolutions, obtained thr…
Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methods
Nicola Cecere, Andrea Bacciu, Ignacio Fernández TobÃas +1
Uncertainty quantification (UQ) in Large Language Models (LLMs) is essential for their safe and reliable deployment, particularly in critical applications where incorrect outputs c…
STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing
Andrea Alfarano, Alberto Alfarano, Linda Friso +3
Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past f…