1 citations · 1 across the 4 of their papers we have counts for
5 papers
Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label pointing at t…
One Human, Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
A single human must audit LLM agents under a budget of audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated…
Who framed Roger Reindeer? De-censorship of Facebook posts by snippet classification
Fabio Del Vigna, Marinella Petrocchi, Alessandro Tommasi +2
This paper considers online news censorship and it concentrates on censorship of identities. Obfuscating identities may occur for disparate reasons, from military to judiciary ones…
Mining Worse and Better Opinions. Unsupervised and Agnostic Aggregation of Online Reviews
Michela Fazzolari, Marinella Petrocchi, Alessandro Tommasi +1
In this paper, we propose a novel approach for aggregating online reviews, according to the opinions they express. Our methodology is unsupervised - due to the fact that it does no…
Semi-supervised knowledge extraction for detection of drugs and their effects
Fabio Del Vigna, Marinella Petrocchi, Alessandro Tommasi +2
New Psychoactive Substances (NPS) are drugs that lay in a grey area of legislation, since they are not internationally and officially banned, possibly leading to their not prosecut…