3 papers
cs.CL2026
Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations
Alessandro Morosini, Wei Sun, Georgia Perakis
Large language model (LLM) assistants are increasingly used in multi-turn conversations, where the user's intent is often unclear at first and revealed only gradually over time. Th…
cs.CL2026
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
Alessandro Morosini, Sarah H. Cen, Andrew Ilyas +3
Personalization algorithms determine what content users encounter on online platforms. Auditing these systems is difficult because independent auditors have only black-box access t…
cs.LG2026
Too Sharp, Too Sure: When Calibration Follows Curvature
Alessandro Morosini, Matea Gjika, Tomaso Poggio +1
Modern neural networks can achieve high accuracy while remaining poorly calibrated, producing confidence estimates that do not match empirical correctness. Yet calibration is often…