14 papers
Credal Large Language Models for Semantic Commitment under Uncertainty
Shireen Kudukkil Manchingal, Sofiia Nikolenko, Fabio Cuzzolin
Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a sing…
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Sofiia Nikolenko, Michele Papucci, Mina Rezaei +1
Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training. While most…
Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning
Shireen Kudukkil Manchingal, Abhey Kalia, Fernanda Gonçalves +1
When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appear correct while the output as…
Random-Set Graph Neural Networks
Tommy Woodley, Shireen Kudukkil Manchingal, Matteo Tolloso +2
Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities…
A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification
Ezel Kilicdere, Shireen Kudukkil Manchingal, Fabio Cuzzolin
Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and freq…
Credal and Interval Deep Evidential Classifications
Michele Caprio, Shireen K. Manchingal, Fabio Cuzzolin
Uncertainty Quantification (UQ) presents a pivotal challenge in the field of Artificial Intelligence (AI), profoundly impacting decision-making, risk assessment and model reliabili…