TeachLM：利用真实学习数据对教育大语言模型进行后训练
TeachLM: Post-Training LLMs for Education Using Authentic Learning Data
AI总结：
针对大语言模型教育应用缺乏真实训练数据的问题，提出TeachLM，利用10万小时真实师生互动数据微调模型，显著提升对话教学性能。
摘要：
生成式人工智能彻底改变教育的潜力受到大语言模型（LLMs）教学局限性的制约。一个主要问题是缺乏反映真实学生学习过程的高质量训练数据。提示工程作为一种临时解决方案应运而生，但提示以基于规则的自然语言编码复杂教学策略的能力本质上是有限的。为解决这一差距，我们引入了TeachLM——一种通过对最先进模型进行参数高效微调而优化的教学大语言模型。TeachLM在由Polygence维护的包含10万小时一对一纵向学生-导师交互的数据集上进行训练，该数据集经过严格匿名化处理以保护隐私。我们利用参数高效微调开发了一个真实学生模型，能够生成高保真的合成学生-导师对话。基于此能力，我们提出了一种新颖的多轮评估协议，利用合成对话生成来提供对大语言模型对话能力的快速、可扩展且可复现的评估。我们的评估表明，在真实学习数据上进行微调显著提升了对话和教学性能——学生发言时间翻倍，提问风格得到改进，对话轮次增加50%，并且教学个性化程度更高。
英文摘要：
The promise of generative AI to revolutionize education is constrained by the pedagogical limits of large language models (LLMs). A major issue is the lack of access to high-quality training data that reflect the learning of actual students. Prompt engineering has emerged as a stopgap, but the ability of prompts to encode complex pedagogical strategies in rule-based natural language is inherently limited. To address this gap we introduce TeachLM - an LLM optimized for teaching through parameter-efficient fine-tuning of state-of-the-art models. TeachLM is trained on a dataset comprised of 100,000 hours of one-on-one, longitudinal student-tutor interactions maintained by Polygence, which underwent a rigorous anonymization process to protect privacy. We use parameter-efficient fine-tuning to develop an authentic student model that enables the generation of high-fidelity synthetic student-tutor dialogues. Building on this capability, we propose a novel multi-turn evaluation protocol that leverages synthetic dialogue generation to provide fast, scalable, and reproducible assessments of the dialogical capabilities of LLMs. Our evaluations demonstrate that fine-tuning on authentic learning data significantly improves conversational and pedagogical performance - doubling student talk time, improving questioning style, increasing dialogue turns by 50%, and greater personalization of instruction.
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。
