Hi, I’m Beyza!
I am a PhD student at the Conversational AI Lab at the University of Illinois at Urbana-Champaign (UIUC), advised by Dr. Dilek Hakkani-Tur and Dr. Gokhan Tur.
My research sits at the intersection of AI safety and alignment, with a particular interest in the reliability of multi-agent interactions—how AI systems behave, influence one another, and maintain trustworthy behavior in increasingly autonomous settings. Within this broader agenda, I am currently focused on computational persuasion: how conversational AI systems can be used to persuade, how they can be manipulated through persuasive inputs, and how AI can play a role in evaluating and safeguarding persuasive interactions. I am especially drawn to the challenge of teaching models to selectively resist persuasion, a problem that sits at the heart of safe and trustworthy AI deployment.
Prior to joining UIUC, I received my B.S. in Computer Science and Mathematics from the University of Arizona in 2024. During my undergraduate studies, I worked with Dr. Steve Bethard from the CLU Lab on the tasks of multilingual intimacy analysis and spoiler detection and generation.
Recent Publications
Must Read: A Comprehensive Survey of Computational Persuasion
paper (ACM Computing Surveys 2026)Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
paper (Workshop on Multi-Turn Interactions in Large Language Models @ NeurIPS 2025)Language Specific Knowledge: Do Models Know Better in X than in English?
paper (Preprint 2025)