Zahra Ashktorab

Research Staff Member at IBM Research

I specialize in Human-AI Interaction, Conversational AI, and Fairness in Machine Learning. My research focuses on creating better outcomes in human-AI collaboration through understanding user mental models, improving conversational systems, and ensuring equitable AI technologies.

View My Research Get In Touch

About Me

I am a Research Staff Member at IBM Research where I investigate factors that enable better outcomes in human-AI interaction. My research spans multiple areas including user mental models of AI agents, repair approaches in conversational breakdowns, the impact of AI identity disclosure and communication directionality on collaboration outcomes, and user reliance in human-AI interaction.

Most recently, I am examining the role of humans in the evaluation of Large Language Models (LLMs) in the context of LLM-as-a-judge, contributing to the critical understanding of how we assess and validate AI systems.

Prior to joining IBM Research in 2017, I graduated with a Ph.D. in Human Computer Interaction from the University of Maryland, College Park. During my Ph.D., I completed multiple internships at IBM Research (Almaden), Microsoft Research (Cambridge, UK), and Data Science for Social Good.

Research Interests

Human-AI Interaction

Understanding how humans interact with AI systems, including mental models, trust, and collaboration patterns.

Conversational AI

Developing and improving conversational systems, including repair strategies.

Fairness & Ethics

Ensuring equitable AI technologies and understanding practitioner perspectives on fairness in ML.

LLM-as-a-Judge

Examining how large language models can act as evaluators (“LLM-as-a-judge”), examining their strategies, front-end designs, and human-AI interactions.