用多阶段AI pipeline从课件自动生成教学级问答
Slide Deck Q&A Quality Assurance App: A Multi-Stage Pipeline for Pedagogical Question Generation
- 四阶段LLM流程融合图文信息，按教学逻辑生成问题
- 可过滤非教学内容，生成高保真、无冗余的问答集
- 适合教育科技开发者和课程设计者快速构建题库
从讲座幻灯片生成高质量、有教学价值的问题很困难，因为关键教学内容同时分布在文本和视觉元素中，且有效问题需基于整个演示文稿的逻辑流进行设计，而非逐页孤立生成。本文介绍Slide Deck Q&A Quality Assurance（slidesqaqa），一个基于Flask的软件系统，可从PDF幻灯片中提取文字和渲染图像，并通过包含窗口规划、幻灯片合成、幻灯片标注和一致性校验的四阶段大语言模型流水线进行处理。该系统联合推理幻灯片模态与教学角色，分配有限的问题预算，并在幻灯片集层面修订草稿标注以减少冗余并提升覆盖度。最终输出为结构化JSON，包含幻灯片集目标、章节结构、每页摘要、问题集及评估分数。在两个技术类讲座幻灯片上的初步实验表明，该流水线能有效过滤非教学内容，并生成针对视觉复杂内容的高保真、教学连贯问题。现运行系统地址：https://slidesqaqa-974767694043.us-west1.run.app，代码仓库：https://github.com/blinding2submit/slidesqaqa
原文摘要 · Abstract (English)
Generating high-quality, pedagogically useful questions from lecture slide decks is difficult because important instructional content is distributed across both text and visual elements, and because useful questions must be scaffolded across the flow of a presentation rather than generated slide by slide in isolation. This paper describes Slide Deck Q\&A Quality Assurance (slidesqaqa), a Flask-based software system that extracts text and rendered images from PDF slides and processes them through a four-stage large language model pipeline comprising window planning, deck synthesis, slide annotation, and reconciliation. The system reasons jointly about slide modality and pedagogical role, allocates bounded question budgets, and revises draft annotations at the deck level to reduce redundancy and improve coverage. The final output is a structured JSON annotation containing deck-level goals, section structure, slide-level summaries, question sets, and evaluation scores. Initial experiments on two technical lecture decks indicate that the pipeline can filter non-instructional slides and produce high-fidelity, pedagogically coherent questions for visually complex content. The working system is at https://slidesqaqa-974767694043.us-west1.run.app The software repository is at https://github.com/blinding2submit/slidesqaqa
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。