使用LLMs和知识图谱引导推理建模学生意义建构
Modeling Student Sensemaking with LLMs and Knowledge-Graph-Guided Inference
浏览论文内容
中文总结 AI 辅助
本研究探讨了指令调优的大语言模型在无需任务特定训练下，能否通过知识状态信息辅助，对协作科学学习中的学生意义建构进行多维分析，并发现推理提示和知识状态诊断能提升对不成功案例的识别，但无单一配置全面最优。
中文摘要 AI 辅助
协作科学学习需要对学生的对话进行细致解读，以刻画学习者如何识别知识差距、构建解释并努力达成解决方案——这是一种理论驱动的分析，劳动密集且难以规模化。我们研究指令调优的大语言模型（LLMs）能否在无需任务特定训练的情况下支持协作意义建构的多维分析，以及结构化的知识状态信息是否能改进模型推理。我们在23个带有丰富标注、专家标记的片段上评估了两个中等规模的LLMs，这些片段跨越了变化定义脚手架、推理模式和轮次结构的提示条件。在没有推理的情况下，模型倾向于过度预测成功的意义建构；启用推理的提示改进了对不成功案例的识别。知识状态诊断提供了额外的依据，改善了对不成功意义建构的检测，并增加了与专家标注的一致性。没有单一配置在所有意义建构维度上表现最佳，这凸显了任务的多维性质。
英文摘要
Collaborative science learning requires nuanced interpretation of student dialogue to characterize how learners identify knowledge gaps, build explanations, and work toward resolution - a theory-driven analysis that is labor-intensive and difficult to scale. We investigate whether instruction-tuned large language models (LLMs) can support multidimensional analysis of collaborative sensemaking without task-specific training, and whether structured knowledge-state information improves model inference. We evaluate two mid-size LLMs on 23 richly annotated, expert-labeled episodes across prompting conditions that vary definitional scaffolding, reasoning mode, and turn structure. Without reasoning, models tend to overpredict successful sensemaking; reasoning-enabled prompting improves identification of unsuccessful cases. Knowledge-state diagnostics provide additional grounding, improving detection of unsuccessful sensemaking and increasing agreement with expert annotations. No single configuration performs best across all sensemaking dimensions, underscoring the multidimensional nature of the task.
发表机构
- LMU München（慕尼黑大学）
- Gazi University（加齐大学）
机构由 AI 辅助整理，请以论文原文为准。
