← Search

Roberto Di Pietro

2 accepted papers

2026

A Geometric Analysis of Small-sized Language Model Hallucinations

ICML 2026poster

Hallucinations---fluent but factually incorrect responses---pose a major challenge to the reliability of language models, especially in multi-step or agentic settings. This work investigates hallucinations in small-sized LLMs through a geometric perspective, starting from the hypothesis that when mo…

Cited by 0SourceScholar
2020

A Survey on Computational Propaganda Detection

IJCAI 2020poster

Propaganda campaigns aim at influencing people's mindset with the purpose of advancing a specific agenda. They exploit the anonymity of the Internet, the micro-profiling ability of social networks, and the ease of automatically creating and managing coordinated networks of accounts, to reach million…

Cited by 0SourcePDFScholar