CLASS：一个基于学习科学原则构建智能导学系统的设计框架
CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principles
AI总结：
本文提出CLASS设计框架，通过脚手架数据集和动态对话数据集赋予基于大语言模型的智能导学系统逐步指导与自然交互能力，并基于该框架构建了面向大学入门生物学的SPOCK系统，获得专家好评。
摘要：
我们提出了一个名为“基于分析式分步策略的对话式学习”（Conversational Learning with Analytical Step-by-Step Strategies，CLASS）的设计框架，用于构建由高性能大语言模型（LLMs）驱动的高级智能导学系统（ITS）。CLASS框架赋予ITS两项关键能力。第一，通过精心构建的脚手架数据集，CLASS使ITS具备基本的问题解决策略，从而能够向学生提供类似人类导师的逐步指导。第二，通过使用动态对话数据集，CLASS帮助ITS促进自然语言交互，培育有吸引力的学生与导师对话。CLASS框架还为ITS的内部决策过程提供了有价值的洞察，这使得用户反馈能够无缝集成，从而实现持续改进和优化。我们还展示了一个概念验证型ITS，称为SPOCK，它使用CLASS框架进行训练，重点关注大学入门级生物学内容。我们为SPOCK的初步评估制定了一个精心设计的协议，考察其回答的事实准确性和相关性等方面。生物学领域的专家给出了积极评价，特别强调了SPOCK能够将问题分解为可管理的子问题，并向学生提供鼓励性回应。代码和模型可在https://github.com/luffycodes/Tutorbot-Spock获取。
英文摘要：
We present a design framework called Conversational Learning with Analytical Step-by-Step Strategies (CLASS) for building advanced Intelligent Tutoring Systems (ITS) powered by high-performance Large Language Models (LLMs). The CLASS framework empowers ITS with two key capabilities. First, through a carefully curated scaffolding dataset, CLASS equips ITS with essential problem-solving strategies, enabling it to provide tutor-like, step-by-step guidance to students. Second, by using a dynamic conversational dataset, CLASS assists ITS in facilitating natural language interactions, fostering engaging student-tutor conversations. The CLASS framework also provides valuable insights into ITS' internal decision-making process which allows seamless integration of user feedback, thus enabling continuous refinement and improvement. We also present a proof-of-concept ITS, referred to as SPOCK, which is trained using the CLASS framework with a focus on introductory college-level biology content. A carefully constructed protocol was developed for SPOCK's preliminary evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting SPOCK's capability to break down questions into manageable subproblems and provide encouraging responses to students. Code and models are available at https://github.com/luffycodes/Tutorbot-Spock.
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。
