@inproceedings{balog-bakken-2026-act,
title = "``Act Like a 5th Grader'' is Not Enough: Bounding Knowledge in {LLM}-Based User Simulators",
author = "Balog, Krisztian and
Bakken, Arild Michel",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2367/",
doi = "10.18653/2026.findings-emnlp.2367",
pages = "50860--50878",
ISBN = "979-8-89176-462-0",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balog-bakken-2026-act">
<titleInfo>
<title>“Act Like a 5th Grader” is Not Enough: Bounding Knowledge in LLM-Based User Simulators</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krisztian</namePart>
<namePart type="family">Balog</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arild</namePart>
<namePart type="given">Michel</namePart>
<namePart type="family">Bakken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">balog-bakken-2026-act</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2367</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2367/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>50860</start>
<end>50878</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Act Like a 5th Grader” is Not Enough: Bounding Knowledge in LLM-Based User Simulators
%A Balog, Krisztian
%A Bakken, Arild Michel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F balog-bakken-2026-act
%X 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.
%R 10.18653/2026.findings-emnlp.2367
%U https://aclanthology.org/2026.findings-emnlp.2367/
%U https://doi.org/10.18653/2026.findings-emnlp.2367
%P 50860-50878
Markdown (Informal)
[“Act Like a 5th Grader” is Not Enough: Bounding Knowledge in LLM-Based User Simulators](https://aclanthology.org/2026.findings-emnlp.2367/) (Balog & Bakken, Findings 2026)
ACL