arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13243cs.CYcs.AI
收藏

评判评判者:人类验证多LLM评估用于高质量K-12科学教学材料

Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials

Washington State University, Pullman, WA, USA(华盛顿州立大学);University at Buffalo, State University of New York, Buffalo, NY, USA(布法罗大学)

Peng He, Zhaohui Li, Zeyuan Wang, Jinjun Xiong, Tingting Li

AI总结:

本研究通过人类专家验证多LLM评估,揭示LLM在K-12科学教学材料设计中的推理优劣,为生成式AI代理的发展提供指导。

摘要:

设计高质量且符合标准的K-12科学教学材料是耗时且需要专业知识的。本研究探讨了专家在审查AI生成的此类材料评估时注意到什么,旨在将他们的见解转化为未来基于生成式AI的教学材料设计代理的设计原则。我们有意选择了12个高质量的课程单元,涵盖生命科学、物理科学和地球科学,这些单元来自经过验证的项目,如OpenSciEd和基于项目的学习中的多重语文。使用EQuIP评估量表的9个评估项目,我们要求GPT-4o、Claude和Gemini为每个单元生成数值评分和书面理由,生成648个评估输出。两位科学教育专家独立审查所有输出,对评分和理由进行一致(1)或不一致(0)的标记,并提供对AI推理的定性反思。这一过程揭示了LLM判断与专家观点一致或不一致的模式,揭示了推理的优势、差距和情境细微差别。这些见解将直接指导开发一个领域特定的生成式AI代理,以支持K-12科学教育中高质量教学材料的设计。

英文摘要:

Designing high-quality, standards-aligned instructional materials for K--12 science is time-consuming and expertise-intensive. This study examines what human experts notice when reviewing AI-generated evaluations of such materials, aiming to translate their insights into design principles for a future GenAI-based instructional material design agent. We intentionally selected 12 high-quality curriculum units across life, physical, and earth sciences from validated programs such as OpenSciEd and Multiple Literacies in Project-based Learning. Using the EQuIP rubric with 9 evaluation items, we prompted GPT-4o, Claude, and Gemini to produce numerical ratings and written rationales for each unit, generating 648 evaluation outputs. Two science education experts independently reviewed all outputs, marking agreement (1) or disagreement (0) for both scores and rationales, and offering qualitative reflections on AI reasoning. This process surfaces patterns in where LLM judgments align with or diverge from expert perspectives, revealing reasoning strengths, gaps, and contextual nuances. These insights will directly inform the development of a domain-specific GenAI agent to support the design of high-quality instructional materials in K--12 science education.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑