5 papers
The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
Giovanni Servedio, Potito Aghilar, Alessio Mattiace +6
Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its re…
RUVA: Personalized Transparent On-Device Graph Reasoning
Gabriele Conte, Alessio Mattiace, Gianni Carmosino +6
The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a funda…
Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
Alessandro De Bellis, Salvatore Bufi, Giovanni Servedio +3
Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retra…
Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs
Giovanni Servedio, Alessandro De Bellis, Dario Di Palma +2
Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent stud…
LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing
Dario Di Palma, Alessandro De Bellis, Giovanni Servedio +3
Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. H…