arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04302cs.LG
收藏

表征对齐支持有效的机器教学

Representational Alignment Supports Effective Machine Teaching

New York University(纽约大学);University of Cambridge(剑桥大学);Max Planck Institute for Empirical Aesthetics(马克斯·普朗克经验美学研究所);Anthropic(Anthropic公司);Massachusetts Institute of Technology(麻省理工学院);University College London(伦敦大学学院);University of California, Berkeley(加州大学伯克利分校);Princeton University(普林斯顿大学)
Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya, Nori Jacoby, Weiyang Liu, Theodore R. Sumers, Michalis Korakakis, Umang Bhatt, Mark Ho, Joshua B. Tenenba… 展开作者

Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya, Nori Jacoby, Weiyang Liu, Theodore R. Sumers, Michalis Korakakis, Umang Bhatt, Mark Ho, Joshua B. Tenenbaum, Brad Love, Zachary A. Pardos, Adrian Weller, Thomas L. Griffiths

AI总结:

本文提出受控实验设置GRADE,发现教师与学生的表征对齐能提升学习效果,并受班级规模和多样性调节,进而设计GRADE-Match优化师生匹配,强调机器教师应兼顾准确率与表征对齐。

摘要:

一位好老师不仅应当知识渊博,还应当能够以学生理解的方式进行沟通——即共享学生对世界的表征。在本工作中,我们引入了一个新的受控实验设置 GRADE,用于研究教学法与表征对齐。我们通过一系列机器-机器和机器-人类教学实验使用 GRADE,刻画出一条效用曲线,定义了表征对齐、教师专业水平与学生学业成果之间的关系。我们发现,与学生之间更好的表征对齐能够改善学生的学业成果(即任务准确率),但这种效应会受到所教班级规模及其表征多样性的调节。我们利用这些见解设计了一个初步的课堂匹配流程 GRADE-Match,用于优化学生与教师之间的分配。在设计机器教师时,我们的结果表明,不仅要关注准确率,还要关注与人类学习者之间的表征对齐,这一点十分重要。

英文摘要:

A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world. In this work, we introduce a new controlled experimental setting, GRADE, to study pedagogy and representational alignment. We use GRADE through a series of machine-machine and machine-human teaching experiments to characterize a utility curve defining a relationship between representational alignment, teacher expertise, and student learning outcomes. We find that improved representational alignment with a student improves student learning outcomes (i.e., task accuracy), but that this effect is moderated by the size and representational diversity of the class being taught. We use these insights to design a preliminary classroom matching procedure, GRADE-Match, that optimizes the assignment of students to teachers. When designing machine teachers, our results suggest that it is important to focus not only on accuracy, but also on representational alignment with human learners.

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。

↑