SABA GHANBARI HAEZ

Research Interests: Trustworthy Conversational AI; Safe Autonomy; Bias Investigation and Mitigation; Fairness in Dialogue Systems; User Autonomy; Safety of Large Language Models.

Bio: Saba holds a Master’s degree in Linguistics and Language Studies. She is currently pursuing a PhD in Computer Science at Fondazione Bruno Kessler (FBK) and the University of Bolzano (UniBZ). Within FBK’s Intelligent Digital Agents (IDA) research unit, she focuses on developing ethical and trustworthy conversational AI using Large Language Models (LLMs). Her research focuses on safe autonomy in dialogue systems — including bias detection and mitigation, preserving user autonomy, and reducing hallucinations to improve the reliability of LLM-powered interactions