@inproceedings{kim-boggust-2026-people,
title = "What People Almost Did: Evaluating {LLM} Social Simulations Beyond Behavioral Fit",
author = "Kim, JaeWon and
Boggust, Angie",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.88/",
pages = "1263--1269",
ISBN = "979-8-89176-485-9",
abstract = "LLM-based social simulations are primarily evaluated for behavioral fit, testing whether agents reproduce the actions or response distributions of the people they are simulating. However, the promise of simulation extends beyond behavioral fit. Simulations can explain human behavior, diagnose barriers, and compare large-scale interventions. These use cases depend on understanding $\textit{why}$ people acted a certain way, not just $\textit{what}$ they did. As a result, behavioral fit is insufficient for these types of claims because behavior underdetermines the reasoning process behind it. For instance, the behavior of staying silent may be due to disinterest or suppressed speech, and not answering a call may be due to distrust of the caller or limited phone access. In this paper, we propose $\textit{representational adequacy}$ as a new evaluation target for LLM-based social simulations. By leveraging LLM reasoning traces, representational adequacy measures whether a simulation{'}s scenario{--}reasoning{--}action triples preserve the reasoning process behind the behavior in a way that is faithful to the population and scenarios being simulated. We distinguish representational adequacy from interpretability and alignment metrics, propose ways to integrate it into simulation research, and pose its measurement as an open problem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-boggust-2026-people">
<titleInfo>
<title>What People Almost Did: Evaluating LLM Social Simulations Beyond Behavioral Fit</title>
</titleInfo>
<name type="personal">
<namePart type="given">JaeWon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angie</namePart>
<namePart type="family">Boggust</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>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>LLM-based social simulations are primarily evaluated for behavioral fit, testing whether agents reproduce the actions or response distributions of the people they are simulating. However, the promise of simulation extends beyond behavioral fit. Simulations can explain human behavior, diagnose barriers, and compare large-scale interventions. These use cases depend on understanding why people acted a certain way, not just what they did. As a result, behavioral fit is insufficient for these types of claims because behavior underdetermines the reasoning process behind it. For instance, the behavior of staying silent may be due to disinterest or suppressed speech, and not answering a call may be due to distrust of the caller or limited phone access. In this paper, we propose representational adequacy as a new evaluation target for LLM-based social simulations. By leveraging LLM reasoning traces, representational adequacy measures whether a simulation’s scenario–reasoning–action triples preserve the reasoning process behind the behavior in a way that is faithful to the population and scenarios being simulated. We distinguish representational adequacy from interpretability and alignment metrics, propose ways to integrate it into simulation research, and pose its measurement as an open problem.</abstract>
<identifier type="citekey">kim-boggust-2026-people</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.88/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1263</start>
<end>1269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What People Almost Did: Evaluating LLM Social Simulations Beyond Behavioral Fit
%A Kim, JaeWon
%A Boggust, Angie
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F kim-boggust-2026-people
%X LLM-based social simulations are primarily evaluated for behavioral fit, testing whether agents reproduce the actions or response distributions of the people they are simulating. However, the promise of simulation extends beyond behavioral fit. Simulations can explain human behavior, diagnose barriers, and compare large-scale interventions. These use cases depend on understanding why people acted a certain way, not just what they did. As a result, behavioral fit is insufficient for these types of claims because behavior underdetermines the reasoning process behind it. For instance, the behavior of staying silent may be due to disinterest or suppressed speech, and not answering a call may be due to distrust of the caller or limited phone access. In this paper, we propose representational adequacy as a new evaluation target for LLM-based social simulations. By leveraging LLM reasoning traces, representational adequacy measures whether a simulation’s scenario–reasoning–action triples preserve the reasoning process behind the behavior in a way that is faithful to the population and scenarios being simulated. We distinguish representational adequacy from interpretability and alignment metrics, propose ways to integrate it into simulation research, and pose its measurement as an open problem.
%U https://aclanthology.org/2026.realm-1.88/
%P 1263-1269
Markdown (Informal)
[What People Almost Did: Evaluating LLM Social Simulations Beyond Behavioral Fit](https://aclanthology.org/2026.realm-1.88/) (Kim & Boggust, REALM 2026)
ACL