arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.15280cs.HCcs.AI
收藏

基于大语言模型的多模态反馈在学习效果和学生感知上与教师反馈相当且更优

LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback

Carnegie Mellon University(卡内基梅隆大学);The University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);The University of Hong Kong(香港大学)

Chloe Qianhui Zhao, Jie Cao, Jionghao Lin, Kenneth R. Koedinger

AI总结:

本文提出一种实时AI辅助的多模态反馈系统,通过整合结构化文本解释与动态多媒体资源,实现学习效果与学生感知的提升,证明AI反馈在清晰度、具体性等方面优于传统教师反馈。

摘要:

提供及时、针对性和多模态的反馈有助于学生快速纠正错误、建立深入理解并保持动力,但大规模实施仍具挑战。本研究引入了一种实时AI辅助的多模态反馈系统,整合了结构化文本解释与动态多媒体资源,包括检索到的最相关幻灯片页面参考和流式AI音频讲解。在一项在线众包实验中,我们比较了该系统与固定传统教师反馈在三个维度上的表现:(1) 学习效果,(2) 学习者参与度,(3) 感知的反馈质量和价值。结果显示,AI多模态反馈在学习增益上与原始教师反馈相当,同时在清晰度、具体性、简洁性、动机、满意度和减少认知负荷方面显著优于传统反馈,同时在正确性、信任和接受度方面具有可比性。过程日志揭示了不同的参与模式:对于多选题,教师反馈鼓励更多提交;对于开放性问题,AI辅助的针对性建议降低了修改障碍并促进了迭代改进。这些发现突显了AI多模态反馈在提供可扩展、实时和上下文感知支持方面的潜力,这既减少了教师的工作量,又提升了学生体验。

英文摘要:

Providing timely, targeted, and multimodal feedback helps students quickly correct errors, build deep understanding and stay motivated, yet making it at scale remains a challenge. This study introduces a real-time AI-facilitated multimodal feedback system that integrates structured textual explanations with dynamic multimedia resources, including the retrieved most relevant slide page references and streaming AI audio narration. In an online crowdsourcing experiment, we compared this system against fixed business-as-usual feedback by educators across three dimensions: (1) learning effectiveness, (2) learner engagement, (3) perceived feedback quality and value. Results showed that AI multimodal feedback achieved learning gains equivalent to original educator feedback while significantly outperforming it on perceived clarity, specificity, conciseness, motivation, satisfaction, and reducing cognitive load, with comparable correctness, trust, and acceptance. Process logs revealed distinct engagement patterns: for multiple-choice questions, educator feedback encouraged more submissions; for open-ended questions, AI-facilitated targeted suggestions lowered revision barriers and promoted iterative improvement. These findings highlight the potential of AI multimodal feedback to provide scalable, real-time, and context-aware support that both reduces instructor workload and enhances student experience.

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。

↑