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 2606.01375cs.CYcs.AI
收藏

超越访问:引导式LLM支架在本科统计学自主学习中的应用

Beyond Access: Guided LLM Scaffolding for Independent Learning in Undergraduate Statistics

School of Electrical and Computer Engineering, University of Tehran, Iran(伊朗塔里哈大学电气与计算机工程学院);Tehran Institute for Advanced Studies, Khatam University, Iran(伊朗卡塔姆大学泰赫兰高级研究院)

Mohammad Amanlou, Yasaman Amou-Jafari, Fereshte Bagheri, Fatemeh Boloukazari, Mehrad Liviyan, Elahe Khodaverdi Nadrabadi, Shahab Sherafat, Behnam Bahrak

AI总结:

本研究通过准实验比较无LLM、无限制LLM和引导式LLM三种条件,发现引导式LLM使用能促进以推理为导向的交互模式,提升无辅助测验表现,并改善自我评估校准,表明LLM作为教育工具需通过支架设计实现推理伙伴而非答案获取工具。

摘要:

大型语言模型(LLM)正日益进入学生的学习实践,但其教育价值取决于它们是支持推理还是使学生在不参与的情况下完成任务。本研究考察了在本科概率与统计课程中引导式LLM的使用,重点关注分配访问与实际交互质量之间的差距。在一个为期四周的准实验暑期项目中,学生被分为三个平衡条件:无LLM访问、无限制LLM访问和引导式LLM访问。引导条件使用与无限制条件相同的LLM平台,但学生接受了明确的培训和规则,以促进以推理为导向的求助、逐步提示、验证和道德使用。所有测验和延迟的期末考试均在无LLM或外部帮助的情况下完成,使我们能够区分AI支持的练习表现与独立学习。结果表明,与无限制访问相比,引导式使用与更清晰的学习导向交互模式相关,尤其是在优先考虑推理而非最终答案以及请求逐步支持方面。引导式LLM学生在干预阶段的无帮助测验中表现更强,而无限制访问似乎更有助于辅助练习完成,而非持续提高独立表现。可用时间测量不支持简单的基于持续时间的解释,自我评估校准表明在引导式LLM条件下,感知理解与展示理解之间的对齐更好。总体而言,仅提供LLM访问似乎是一种不完整的教育干预。对于人工智能教育(AIED),核心设计挑战是如何搭建支架,使学生使用LLM的方式使这些系统成为推理伙伴而非答案获取工具。

英文摘要:

Large language models (LLMs) are increasingly entering students' learning practices, but their educational value may depend on whether they are used to support reasoning or to complete tasks without engaging in the underlying reasoning. This study examines guided LLM use in an undergraduate Probability and Statistics course, focusing on the distinction between assigned LLM access and the quality of students' actual interaction with the model. In a four-week quasi-experimental summer program, students were organized into three balanced conditions: no LLM access, unrestricted LLM access, and guided LLM access. The guided condition used the same LLM platform as the unrestricted condition, but students received explicit training and rules intended to promote reasoning-focused help-seeking, stepwise hints, verification, and ethical use. All quizzes and the delayed final exam were completed without LLM or external assistance, allowing us to separate AI-supported practice performance from independent learning. Results show that guided use was associated with a clearer learning-oriented interaction pattern than unrestricted access, especially in prioritizing reasoning over final answers and requesting stepwise support. In behavior-defined analyses, Guided-LLM students showed a promising pattern of stronger no-help quiz performance, while practice scores showed no consistent Guided-LLM advantage. Available time measures did not support a simple duration-based explanation, and self-assessment calibration suggested better alignment between perceived and demonstrated understanding in Guided-LLM. These findings suggest that access alone may not reliably distinguish independent performance; instead, the quality of interaction and reasoning-focused scaffolds warrant further study.

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。

↑