把被评测的大模型变成出题助手，用多证据校准编程考题难度，教育评估新思路。
arXiv:2608.07523v1 Announce Type: cross Abstract: Difficulty differences across parallel-class programming examinations affect the fairness of course …
正确不等于会教：教学适宜性指数帮AI导师匹配学生真实水平，避免“答非所问”。
arXiv:2608.05411v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as AI tutors, but a correct answer is not always a …
用知识蒸馏技术自动化评估AI导师的教学质量，FATE方法为教育大模型评价提供新思路
arXiv:2607.10647v1 Announce Type: new Abstract: The rapid integration of Large Language Models (LLMs) into K-12 and higher education has outpaced the …
语料库驱动AI方法生成的选择题选项可能存在频率偏差，警惕其教育应用中的隐藏陷阱。
arXiv:2602.17377v2 Announce Type: replace Abstract: In recent years, corpus-driven AI methods, such as Large Language Models (LLMs), have seen widespr…
新论文提出FeedEval框架，教学对齐评估LLM生成的作文反馈，为教育场景优化AI输出质量。
arXiv:2601.04574v2 Announce Type: replace Abstract: Going beyond the prediction of numerical scores, recent research in automated essay scoring has in…
一种基于证据诊断的干预训练方法，让大模型评分时严格遵循给定规则，提升可靠性与可解释性
arXiv:2606.06350v1 Announce Type: new Abstract: Reliable rubric grading requires more than accurate score prediction. Each judgement must be grounded …