@inproceedings{zhang-etal-2026-enhancing,
title = "Enhancing Situated Cultural Reasoning in Large Language Models via Simulation Learning",
author = "Zhang, Jinghao and
Chen, Shisong and
Jiang, Sihang and
Xiao, Yanghua and
Feng, Hongwei and
Liang, Jiaqing and
HE, Minggui and
Tao, Shimin and
Mahongxia and
Liu, Yilun",
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.53/",
pages = "1079--1101",
ISBN = "979-8-89176-462-0",
abstract = "As large language models(LLMs) are increasingly deployed in real-world applications, they inevitably encounter culturally sensitive scenarios that require applying cultural knowledge or values to the context in order to generate appropriate responses. However, existing research largely treats culture as static knowledge or abstract values, leaving the application of cultural norms in situated interactions underexplored. To address this gap, we first focus on the situated cultural reasoning of LLMs by proposing \textbf{CuSiR}, a simulation learning framework combining simulated scenario and reinforcement learning. We construct datasets covering both knowledge-based and social scenarios and conduct experiments across multiple role perspectives, instructions, settings, and models. Our results indicate that this framework effectively enhances LLMs' ability to apply existing cultural knowledge, thereby improving their performance on tasks set in cultural scenarios. Code files are available at \url{https://github.com/HoganZinger/Simulation_Learning}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-enhancing">
<titleInfo>
<title>Enhancing Situated Cultural Reasoning in Large Language Models via Simulation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinghao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shisong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongwei</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minggui</namePart>
<namePart type="family">HE</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimin</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mahongxia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Liu</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>As large language models(LLMs) are increasingly deployed in real-world applications, they inevitably encounter culturally sensitive scenarios that require applying cultural knowledge or values to the context in order to generate appropriate responses. However, existing research largely treats culture as static knowledge or abstract values, leaving the application of cultural norms in situated interactions underexplored. To address this gap, we first focus on the situated cultural reasoning of LLMs by proposing CuSiR, a simulation learning framework combining simulated scenario and reinforcement learning. We construct datasets covering both knowledge-based and social scenarios and conduct experiments across multiple role perspectives, instructions, settings, and models. Our results indicate that this framework effectively enhances LLMs’ ability to apply existing cultural knowledge, thereby improving their performance on tasks set in cultural scenarios. Code files are available at https://github.com/HoganZinger/Simulation_Learning</abstract>
<identifier type="citekey">zhang-etal-2026-enhancing</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.53/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1079</start>
<end>1101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Situated Cultural Reasoning in Large Language Models via Simulation Learning
%A Zhang, Jinghao
%A Chen, Shisong
%A Jiang, Sihang
%A Xiao, Yanghua
%A Feng, Hongwei
%A Liang, Jiaqing
%A HE, Minggui
%A Tao, Shimin
%A Liu, Yilun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%A Mahongxia
%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 zhang-etal-2026-enhancing
%X As large language models(LLMs) are increasingly deployed in real-world applications, they inevitably encounter culturally sensitive scenarios that require applying cultural knowledge or values to the context in order to generate appropriate responses. However, existing research largely treats culture as static knowledge or abstract values, leaving the application of cultural norms in situated interactions underexplored. To address this gap, we first focus on the situated cultural reasoning of LLMs by proposing CuSiR, a simulation learning framework combining simulated scenario and reinforcement learning. We construct datasets covering both knowledge-based and social scenarios and conduct experiments across multiple role perspectives, instructions, settings, and models. Our results indicate that this framework effectively enhances LLMs’ ability to apply existing cultural knowledge, thereby improving their performance on tasks set in cultural scenarios. Code files are available at https://github.com/HoganZinger/Simulation_Learning
%U https://aclanthology.org/2026.findings-emnlp.53/
%P 1079-1101
Markdown (Informal)
[Enhancing Situated Cultural Reasoning in Large Language Models via Simulation Learning](https://aclanthology.org/2026.findings-emnlp.53/) (Zhang et al., Findings 2026)
ACL
- Jinghao Zhang, Shisong Chen, Sihang Jiang, Yanghua Xiao, Hongwei Feng, Jiaqing Liang, Minggui HE, Shimin Tao, Mahongxia, and Yilun Liu. 2026. Enhancing Situated Cultural Reasoning in Large Language Models via Simulation Learning. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 1079–1101, Budapest, Hungary. Association for Computational Linguistics.