Zifeng Liu - Human–AI Collaboration in Educational Assessment Evaluating AI Generated Distractors

In this talk, Zifeng will discuss the emerging role of generative AI in educational assessment, with a focus on the automatic generation and evaluation of multiple-choice distractors and feedback in computing and AI education. While large language models show strong potential for producing instructional content, important questions remain regarding the quality, pedagogical validity, and alignment of AI-generated materials with human expectations and learning goals. To address these challenges, this line of work examines how students, experts, and AI systems evaluate and co-create assessment components such as distractors and feedback. Through human–AI collaborative evaluation and experimental comparisons, the research investigates how AI-generated distractors are perceived, how their quality can be systematically assessed, and how automated generation can be integrated into authentic educational contexts. The findings highlight both the opportunities and limitations of current models, revealing where AI aligns with expert judgment and where it diverges from human pedagogical reasoning. By shifting the focus from generation alone to human-centered evaluation and collaboration, this work contributes to more reliable, scalable, and pedagogically grounded approaches for integrating generative AI into assessment and feedback design for computing education. Zifeng Liu is a PhD candidate in Educational Technology at the University of Florida. Her research lies at the intersection of artificial intelligence, learning analytics, and computing education, with a focus on human–AI collaboration in assessment, feedback generation, and AI-supported learning environments. This session is brought to you by the Cohere Labs Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. We'd like to extend a special thank you to Rafay Mustafa Leads of our EdTech group for their dedicati