用图模型提升LLM模拟学生的真实性，助力个性化教育研究。
Which Type of Students can LLMs Act? Investigating Authentic Simulation with Graph-based Human-AI Collaborative System
- 构建三阶段人机协作流程，自动生成并筛选高质量学生代理。
- 结合自动化评分与专家校准，图传播使模拟学生更贴近真人表现。
- 揭示哪些学生类型和行为更易被真实模拟，适合教育评估研究者。
尽管大型语言模型（LLMs）正推动数据驱动的智能教育发展，但准确模拟学生仍是规模化教育数据采集、评估与干预设计中的关键瓶颈。当前研究受限于真实交互数据稀缺、专家评估成本高，以及缺乏对LLM模拟能力的大规模系统性分析。为此，我们提出一个三阶段的LLM-人类协同管道，实现高质量学生代理的自动生成与筛选。通过两轮自动化评分（经专家验证）及基于学生相似性图的得分传播模块，提升了评分一致性。实验表明，结合自动化评分、专家校准与图传播的方法，生成的模拟学生在人类判断下更具真实性。进一步分析发现，特定学生画像与行为模式被更忠实模拟，为个性化学习与教育评估研究提供支持。
原文摘要 · Abstract (English)
While rapid advances in large language models (LLMs) are reshaping data-driven intelligent education, accurately simulating students remains an important but challenging bottleneck for scalable educational data collection, evaluation, and intervention design. However, current works are limited by scarce real interaction data, costly expert evaluation for realism, and a lack of large-scale, systematic analyses of LLMs ability in simulating students. We address this gap by presenting a three-stage LLM-human collaborative pipeline to automatically generate and filter high-quality student agents. We leverage a two-round automated scoring validated by human experts and deploy a score propagation module to obtain more consistent scores across the student similarity graph. Experiments show that combining automated scoring, expert calibration, and graph-based propagation yields simulated student that more closely track authentication by human judgments. We then analyze which profiles and behaviors are simulated more faithfully, supporting subsequent studies on personalized learning and educational assessment.
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。