Savaal自动生成高阶理解型问题，助力深度学习。
Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning
- 分三阶段处理文本，提升长文档问答质量
- 生成问题深度比基线高6.5倍（论文）和1.5倍（博士论文）
- 适合教育、知识评估场景，尤其长文本学习
通过问答评估与提升人类学习至关重要，但自动化这一过程仍具挑战。尽管大语言模型在摘要和问答方面表现优异，其生成有助于学习的高质量问题的能力尚未充分探索。本文提出Savaal，一种可扩展的问题生成系统，具备三个目标：(i) 可扩展性，支持从数百页文本中生成问题；(ii) 深度理解能力，生成超越事实记忆的问题以测试概念推理；(iii) 领域无关性，自动覆盖多样知识领域。Savaal采用三阶段处理流程，而非直接将长文档输入LLM。76名专家在71篇论文与博士论文上的评估表明，相较于直接提示基线，Savaal生成的问题在深度理解测试上分别提升6.5倍（博士论文）和1.5倍（论文）。值得注意的是，随着文档长度增加，Savaal在问题质量更高、成本更低方面的优势愈发明显。
原文摘要 · Abstract (English)
Assessing and enhancing human learning through question-answering is vital, yet automating this process remains challenging. While large language models (LLMs) excel at summarization and query responses, their ability to generate meaningful questions for learners is underexplored. We propose Savaal, a scalable question-generation system with three objectives: (i) scalability, enabling question generation from hundreds of pages of text (ii) depth of understanding, producing questions beyond factual recall to test conceptual reasoning, and (iii) domain-independence, automatically generating questions across diverse knowledge areas. Instead of providing an LLM with large documents as context, Savaal improves results with a three-stage processing pipeline. Our evaluation with 76 human experts on 71 papers and PhD dissertations shows that Savaal generates questions that better test depth of understanding by 6.5X for dissertations and 1.5X for papers compared to a direct-prompting LLM baseline. Notably, as document length increases, Savaal's advantages in higher question quality and lower cost become more pronounced.
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。