Open access
Jul 2026
Toward Standardized Interactivity: An AI-Enabled Adaptive Speaking Task for Computer-Delivered Large-Scale Assessment
Two solutions are proposed: LLM-driven response evaluation using question-specific task completion rubrics for adaptive follow-up question selection and item response theory (IRT) scoring accounting for prompt variability to enhance adaptivity in an LLM-enhanced SDS-delivered interview task.
Y. Park, Yigal Attali, Xiaowan Zhang et al.
· Language Testing · 2 citations