Yifan Xu

Yifan Xu is a Research Associate in Civil Engineering and Management and a PhD student in Computer Science, focusing on Explainable Artificial Intelligence (XAI). She explores dialogue-based explanations for rule-based AI systems and ethical challenges in AI ecosystems. Her work includes analyzing deceptive behaviors of LLMs like ChatGPT and developing transparent AI communication methods.

Education:

• PhD in Computer Science (ongoing)

Research Interests: XAI, dialogue systems, rule-based reasoning, ethical AI, and human-AI interaction. She investigates how AI systems can provide understandable explanations through conversational interfaces, particularly in legal and safety-critical contexts like autonomous vehicles.

Key Themes in Research: Her articles address AI deception detection, ethical implications of large language models, and technical frameworks for explainable reasoning. Recent work emphasizes improving trust through transparent AI communication.

Advisors & Collaborations: Supervised by Prof. L. Dennis, J. Collenette, and C. Dixon. Member of the RAI Centre for Robotics and Artificial Intelligence, collaborating on projects involving human-robot interaction and autonomous systems.