CoDAE：通过思维链数据增强使大型语言模型适应教育场景
CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
AI总结：
本文提出CoDAE框架，通过思维链数据增强和针对性对话案例设计，微调开源LLMs以解决其教育场景中过度顺从、响应适应性低和威胁脆弱性等问题，提升教学指导的适宜性和推理支持能力。
摘要：
大型语言模型（LLMs）因其可扩展性和个性化教学潜力，正日益被用作AI导师。然而，现成的LLMs在教育环境中往往表现不佳：它们经常过快揭示答案，未能根据学生的不确定性调整回应，且容易受到情感操纵提示的影响。为应对这些挑战，我们引入了CoDAE，这是一个通过思维链（CoT）数据增强来使LLMs适应教育用途的框架。我们收集了学生与基于ChatGPT的导师之间的真实对话，并使用CoT提示对其进行丰富，以促进逐步推理和符合教学法的指导。此外，我们设计了针对性的对话案例，以明确缓解三个关键局限：过度顺从、响应适应性低和威胁脆弱性。我们在增强数据集的不同变体上对四个开源LLMs进行微调，并在模拟教育场景中使用自动指标和LLM作为评判者的评估方法对它们进行评估。结果表明，使用CoDAE微调的模型提供了更符合教学法的指导，更好地支持推理过程，并有效抵抗过早揭示答案。
英文摘要：
Large Language Models (LLMs) are increasingly employed as AI tutors due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperform in educational settings: they frequently reveal answers too readily, fail to adapt their responses to student uncertainty, and remain vulnerable to emotionally manipulative prompts. To address these challenges, we introduce CoDAE, a framework that adapts LLMs for educational use through Chain-of-Thought (CoT) data augmentation. We collect real-world dialogues between students and a ChatGPT-based tutor and enrich them using CoT prompting to promote step-by-step reasoning and pedagogically aligned guidance. Furthermore, we design targeted dialogue cases to explicitly mitigate three key limitations: over-compliance, low response adaptivity, and threat vulnerability. We fine-tune four open-source LLMs on different variants of the augmented datasets and evaluate them in simulated educational scenarios using both automatic metrics and LLM-as-a-judge assessments. Our results show that models fine-tuned with CoDAE deliver more pedagogically appropriate guidance, better support reasoning processes, and effectively resist premature answer disclosure.
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。
