仅模仿五年级学生还不够：基于大语言模型的用户模拟器中的知识边界
"Act Like a 5th Grader" is Not Enough: Bounding Knowledge in LLM-Based User Simulators
查看机构详情
- University of Stavanger（斯塔万格大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对基于大语言模型的用户模拟器存在的“超人偏差”问题，提出认知受限用户模拟器（CBUS）框架，通过明确建模认知边界提升模拟人类阅读行为的保真度。
中文摘要 AI 辅助
大语言模型（LLMs）越来越多地被用于模拟人类行为，但往往无法表现出符合现实的认知约束，存在“超人偏差”。利用来自2359名4-6年级小学生的超过71000份阅读理解作答数据集，我们证明标准的角色设定提示会产生近乎完美的确定性表现，无法捕捉成长中读者的自然差异。为解决该问题，我们引入认知受限用户模拟器（CBUS），这是一个通过情景瓶颈明确建模年轻读者受限工作记忆的架构框架。在该框架内，我们形式化了两种不同的答题策略以模拟不同的阅读行为。我们的评估表明，明确建模认知边界显著缩小了多个大语言模型主干上的模拟差距，证明实施架构约束比单纯扩大原始模型能力对于高保真模拟更有效。
英文摘要
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.
