We explore the use of small language models (SLMs) for automatic question generation as a complement to the prevalent use of their large counterparts in learning analytics research. We present a novel question generation pipeline that leverages both the text generation and the probabilistic reasoning abilities of SLMs to generate high-quality questions. Adopting a "generate-then-validate" strategy, our pipeline first performs expansive generation to create an abundance of candidate questions and refine them through selective validation based on novel probabilistic reasoning. We conducted two evaluation studies, one with seven human experts and the other with a large language model (LLM), to assess the quality of the generated questions. Most judges (humans or LLMs) agreed that the generated questions had clear answers and generally aligned well with the intended learning objectives. Our findings suggest that an SLM can effectively generate high-quality questions when guided by a well-designed pipeline that leverages its strengths.

翻译：本研究探讨了在自动问题生成任务中应用小型语言模型（SLMs），作为学习分析研究中普遍采用大型语言模型的补充方案。我们提出了一种新型问题生成流程，该流程充分利用SLMs的文本生成与概率推理能力来生成高质量问题。采用"生成-后验证"策略，该流程首先通过扩展生成创建大量候选问题，随后基于创新的概率推理进行选择性验证以优化问题质量。我们开展了两项评估研究：一项由七位领域专家参与，另一项采用大型语言模型（LLM）作为评估者，以系统评估生成问题的质量。多数评审者（人类专家或LLM）一致认为生成的问题具有明确答案，且与预设学习目标高度契合。研究结果表明，当采用能充分发挥其优势的精心设计流程时，小型语言模型能够有效生成高质量问题。