Which type of students can LLMs act? Investigating authentic simulation with graph-based Human–AI collaborative system
AI Open · 2026 · 7 · 142-151
DOI: 10.1016/j.aiopen.2026.05.001 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI Open, 2026. Verfasst von Haoxuan Li und 8 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, H., Yu, J., Cong, X., Dang, Y., Zhang-Li, D., Mi, L., Zhan, Y., Liu, H., & Liu, Z. (2026). Which type of students can LLMs act? Investigating authentic simulation with graph-based Human–AI collaborative system. AI Open, 7, 142-151. https://doi.org/10.1016/j.aiopen.2026.05.001
Vancouver
Li H, Yu J, Cong X, Dang Y, Zhang-Li D, Mi L, et al. Which type of students can LLMs act? Investigating authentic simulation with graph-based Human–AI collaborative system. AI Open. 2026;7:142-151. doi:10.1016/j.aiopen.2026.05.001
BibTeX
@article{Li2026,
author = {Li, Haoxuan and Yu, Jifan and Cong, Xin and Dang, Yang and Zhang-Li, Daniel and Mi, Lu and Zhan, Yisi and Liu, Huiqin and Liu, Zhiyuan},
title = {Which type of students can LLMs act? Investigating authentic simulation with graph-based Human–AI collaborative system},
journal = {AI Open},
year = {2026},
volume = {7},
pages = {142--151},
doi = {10.1016/j.aiopen.2026.05.001}
}
EUVIMED