2 papers
cs.CL2026
From Granular Revision Operations to Meaningful Revision Units: Evaluating LLMs for Revision Boundary Detection
Yu Tian, Andrew Potter, Katerina Christhilf +4
Revision traces provide valuable evidence about students' writing processes, but their usefulness for learning analytics depends on how individual revisions are represented. Automa…
cs.CL2026
Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models
Yu Tian, Linh Huynh, Katerina Christhilf +4
Recent advances in large language models (LLMs) have made automated multiple-choice question (MCQ) generation increasingly feasible; however, reliably producing items that satisfy…