"Act Like a 5th Grader" is Not Enough: Bounding Knowledge in LLM-Based User Simulators

2026-08-30

AI Summary

为解决LLM模拟人类行为时缺乏真实认知限制的问题，通过引入具有认知边界约束的用户模拟器框架CBUS，并采用两种测试策略来更准确地模仿年轻读者的行为。

Abstract

Large language models (LLMs) are increasingly used to simulate human behavior but frequently fail to exhibit realistic cognitive constraints, suffering from a "superhuman bias." Using a dataset of over 71,000 reading comprehension responses from 2,359 primary-school students (grades 4--6), we demonstrate that standard persona prompting yields near-perfect, deterministic performance, failing to capture the natural variance of developing readers. To address this, we introduce the Cognitively Bounded User Simulator (CBUS), an architectural framework that explicitly models the restricted working memory of young readers through an episodic bottleneck. Within this framework, we formalize two distinct test-taking strategies to emulate different reading behaviors. Our evaluation shows that explicitly modeling cognitive bounds significantly narrows the simulation gap across multiple LLM backbones, demonstrating that enforcing architectural constraints is more effective for high-fidelity simulation than simply scaling raw model capabilities.

Problem

• large language models
• cognitive constraints
• superhuman bias

Innovation

• Cognitively Bounded User Simulator
• Episodic Bottleneck
• Test-taking Strategies