增强基于 LLM 的反馈：来自智能辅导系统与学习科学的洞见
Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciences
AI总结：
本文梳理 ITS 反馈生成的理论与实证研究，提出将循证原则融入基于 LLM 的反馈设计、实验与评估，以增强教育反馈的学习效果。
摘要：
教育人工智能（AIED）领域聚焦技术、教育与心理学的交叉，高度强调以共情和理解支持学习者的需求。大型语言模型（LLM）日益凸显，推动了教育场景中可扩展解决方案的发展，包括在智能辅导系统（ITS）中生成不同类型的反馈。然而，使用这些模型的方式往往是直接编写提示词以获取特定信息，在提示词构建方面缺乏坚实的理论基础，也缺乏对其学习影响的实证评估。本工作倡导审慎且关怀性的 AIED 研究：梳理以往关于 ITS 中反馈生成的研究，重点关注其采用的理论框架以及相应设计在实证评估中的功效，随后提出将这些循证原则应用于基于 LLM 的反馈生成的设计、实验和评估阶段的机会。本文的主要贡献包括：倡导在生成式 AI 时代的反馈生成中采用更谨慎、有理论依据的方法；以及为 LLM 驱动的 ITS 提供关于理论和循证反馈设计的实践建议。
英文摘要：
The field of Artificial Intelligence in Education (AIED) focuses on the intersection of technology, education, and psychology, placing a strong emphasis on supporting learners' needs with compassion and understanding. The growing prominence of Large Language Models (LLMs) has led to the development of scalable solutions within educational settings, including generating different types of feedback in Intelligent Tutoring Systems. However, the approach to utilizing these models often involves directly formulating prompts to solicit specific information, lacking a solid theoretical foundation for prompt construction and empirical assessments of their impact on learning. This work advocates careful and caring AIED research by going through previous research on feedback generation in ITS, with emphasis on the theoretical frameworks they utilized and the efficacy of the corresponding design in empirical evaluations, and then suggesting opportunities to apply these evidence-based principles to the design, experiment, and evaluation phases of LLM-based feedback generation. The main contributions of this paper include: an avocation of applying more cautious, theoretically grounded methods in feedback generation in the era of generative AI; and practical suggestions on theory and evidence-based feedback design for LLM-powered ITS.
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。
