Hongfei Yan

From Evaluated Models to Evaluation Aids: A Multi-Evidence Study of LLM-Based Difficulty Calibration for Programming Examinations

AI evidence can serve as an external reference for problem validation, parallel-class fairness discussion, and longitudinal quality tracking, while the model-identity boundary, single-reviewer design, and review-output instability set explicit limits: AI difficulty scales must not be used for individual student evaluat...