从幻灯片到聊天机器人：利用大学课程材料增强大语言模型
From Slides to Chatbots: Enhancing Large Language Models with University Course Materials
AI总结：
本文研究如何通过整合大学课程材料提升大语言模型在计算机科学课程中的表现，比较了RAG和CPT两种策略，并发现多模态RAG在处理包含图像和公式的幻灯片时更有效。
摘要：
大型语言模型（LLMs）近年来发展迅速。LLMs的一个应用是支持教育环境中的学生学习。然而，先前的工作表明，LLMs在大学级计算机科学课程中仍难以准确回答问题。本文研究如何通过整合大学课程材料来增强LLMs在该场景下的性能。关键挑战在于利用多样化的课程材料，如讲座幻灯片和转录文本，这些材料与典型文本语料有显著差异：幻灯片还包含图像和公式等视觉元素，而转录文本包含口语化的、结构松散的语言。我们比较了两种策略，检索增强生成（RAG）和持续预训练（CPT），以扩展LLMs的课程特定知识。对于幻灯片，我们进一步探索了一种多模态RAG方法，其中将检索到的内容以图像形式呈现给生成器。我们的实验发现，鉴于大学课程材料相对较小，RAG比CPT更有效且更高效。此外，在多模态设置中，将幻灯片作为图像纳入显著提高了性能，优于纯文本检索。这些发现突显了开发能更好地支持学习和教学的AI助手的实用策略，我们希望这些发现能激励其他教育场景中的类似努力。
英文摘要：
Large Language Models (LLMs) have advanced rapidly in recent years. One application of LLMs is to support student learning in educational settings. However, prior work has shown that LLMs still struggle to answer questions accurately within university-level computer science courses. In this work, we investigate how incorporating university course materials can enhance LLM performance in this setting. A key challenge lies in leveraging diverse course materials such as lecture slides and transcripts, which differ substantially from typical textual corpora: slides also contain visual elements like images and formulas, while transcripts contain spoken, less structured language. We compare two strategies, Retrieval-Augmented Generation (RAG) and Continual Pre-Training (CPT), to extend LLMs with course-specific knowledge. For lecture slides, we further explore a multi-modal RAG approach, where we present the retrieved content to the generator in image form. Our experiments reveal that, given the relatively small size of university course materials, RAG is more effective and efficient than CPT. Moreover, incorporating slides as images in the multi-modal setting significantly improves performance over text-only retrieval. These findings highlight practical strategies for developing AI assistants that better support learning and teaching, and we hope they inspire similar efforts in other educational contexts.
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。
