@inproceedings{wu-etal-2026-thinking,
title = "Thinking Alignment of Scenario-Oriented User Simulation",
author = "Wu, Xiaoting and
Huang, Yi and
Gao, Chunyang and
Guo, Mengfei and
Yao, Jingyu and
Feng, Junlan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1989/",
pages = "42932--42945",
ISBN = "979-8-89176-390-6",
abstract = "Existing user simulators based on prompting to role-play or SFT are generally confined to imitating users' textual utterances, without adequately considering the multi-faceted cognitive processes that underlie human decision-making during interactions. To facilitate better alignment with real human thinking patterns, we construct the LMSYS-UserThinking dataset, in which we augment 51k human{--}LLM conversations by reconstructing the user{'}s inner reasoning both during and at the end of each dialogue. Furthermore, to enhance controllability and situational coherence, we introduce scenario settings that describe the global context and user goals throughout multi-turn conversations. Using this dataset, we train user simulators called ThinkingUS on different base models. We evaluate our approach from both offline and online user simulation perspectives, ultimately demonstrating its effectiveness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-thinking">
<titleInfo>
<title>Thinking Alignment of Scenario-Oriented User Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoting</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengfei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyu</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junlan</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Existing user simulators based on prompting to role-play or SFT are generally confined to imitating users’ textual utterances, without adequately considering the multi-faceted cognitive processes that underlie human decision-making during interactions. To facilitate better alignment with real human thinking patterns, we construct the LMSYS-UserThinking dataset, in which we augment 51k human–LLM conversations by reconstructing the user’s inner reasoning both during and at the end of each dialogue. Furthermore, to enhance controllability and situational coherence, we introduce scenario settings that describe the global context and user goals throughout multi-turn conversations. Using this dataset, we train user simulators called ThinkingUS on different base models. We evaluate our approach from both offline and online user simulation perspectives, ultimately demonstrating its effectiveness.</abstract>
<identifier type="citekey">wu-etal-2026-thinking</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1989/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>42932</start>
<end>42945</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thinking Alignment of Scenario-Oriented User Simulation
%A Wu, Xiaoting
%A Huang, Yi
%A Gao, Chunyang
%A Guo, Mengfei
%A Yao, Jingyu
%A Feng, Junlan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wu-etal-2026-thinking
%X Existing user simulators based on prompting to role-play or SFT are generally confined to imitating users’ textual utterances, without adequately considering the multi-faceted cognitive processes that underlie human decision-making during interactions. To facilitate better alignment with real human thinking patterns, we construct the LMSYS-UserThinking dataset, in which we augment 51k human–LLM conversations by reconstructing the user’s inner reasoning both during and at the end of each dialogue. Furthermore, to enhance controllability and situational coherence, we introduce scenario settings that describe the global context and user goals throughout multi-turn conversations. Using this dataset, we train user simulators called ThinkingUS on different base models. We evaluate our approach from both offline and online user simulation perspectives, ultimately demonstrating its effectiveness.
%U https://aclanthology.org/2026.acl-long.1989/
%P 42932-42945
Markdown (Informal)
[Thinking Alignment of Scenario-Oriented User Simulation](https://aclanthology.org/2026.acl-long.1989/) (Wu et al., ACL 2026)
ACL
- Xiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo, Jingyu Yao, and Junlan Feng. 2026. Thinking Alignment of Scenario-Oriented User Simulation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 42932–42945, San Diego, California, United States. Association for Computational Linguistics.