Towards Valid Student Simulation with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Zhihao, Xiao, Yunze, Li, Ming, Xuan, Weihao, Tong, Richard, Diab, Mona, Mitchell, Tom
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918278933250048
author Yuan, Zhihao
Xiao, Yunze
Li, Ming
Xuan, Weihao
Tong, Richard
Diab, Mona
Mitchell, Tom
author_facet Yuan, Zhihao
Xiao, Yunze
Li, Ming
Xuan, Weihao
Tong, Richard
Diab, Mona
Mitchell, Tom
contents This paper presents a conceptual and methodological framework for large language model (LLM) based student simulation in educational settings. The authors identify a core failure mode, termed the "competence paradox" in which broadly capable LLMs are asked to emulate partially knowledgeable learners, leading to unrealistic error patterns and learning dynamics. To address this, the paper reframes student simulation as a constrained generation problem governed by an explicit Epistemic State Specification (ESS), which defines what a simulated learner can access, how errors are structured, and how learner state evolves over time. The work further introduces a Goal-by-Environment framework to situate simulated student systems according to behavioral objectives and deployment contexts. Rather than proposing a new system or benchmark, the paper synthesizes prior literature, formalizes key design dimensions, and articulates open challenges related to validity, evaluation, and ethical risks. Overall, the paper argues for epistemic fidelity over surface realism as a prerequisite for using LLM-based simulated students as reliable scientific and pedagogical instruments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05473
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Valid Student Simulation with Large Language Models
Yuan, Zhihao
Xiao, Yunze
Li, Ming
Xuan, Weihao
Tong, Richard
Diab, Mona
Mitchell, Tom
Computation and Language
Human-Computer Interaction
This paper presents a conceptual and methodological framework for large language model (LLM) based student simulation in educational settings. The authors identify a core failure mode, termed the "competence paradox" in which broadly capable LLMs are asked to emulate partially knowledgeable learners, leading to unrealistic error patterns and learning dynamics. To address this, the paper reframes student simulation as a constrained generation problem governed by an explicit Epistemic State Specification (ESS), which defines what a simulated learner can access, how errors are structured, and how learner state evolves over time. The work further introduces a Goal-by-Environment framework to situate simulated student systems according to behavioral objectives and deployment contexts. Rather than proposing a new system or benchmark, the paper synthesizes prior literature, formalizes key design dimensions, and articulates open challenges related to validity, evaluation, and ethical risks. Overall, the paper argues for epistemic fidelity over surface realism as a prerequisite for using LLM-based simulated students as reliable scientific and pedagogical instruments.
title Towards Valid Student Simulation with Large Language Models
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2601.05473