@inproceedings{li-etal-2025-reinforcement,
title = "A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought Alignment",
author = "Li, Binghui and
Zou, Minghui and
Zhang, Xiaowang and
Chen, Shizhan and
Feng, Zhiyong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1115/",
doi = "10.18653/v1/2025.findings-acl.1115",
pages = "21674--21688",
ISBN = "979-8-89176-256-5",
abstract = "Cross-lingual stance detection identifies users' attitudes toward specific targets in texts by transferring knowledge from source languages to target languages. Previous studies have typically facilitated this transfer by translating and aligning labels or targets. However, these methods cannot effectively perform cross-lingual transfer of the complex reasoning processes in stance detection. To address this challenge, we propose a reinforcement learning framework using cross-lingual Chain-of-Thought (CoT) alignment, referred to as RCCA. Specifically, we adopt a cross-lingual CoT alignment strategy to obtain the high-quality CoTs generated from target language inputs. After that, we leverage reinforcement learning by sampling CoTs and assigning rewards according to predefined rules, aiming to enhance the model{'}s generalization capabilities in the target language. Experimental results on four multilingual datasets demonstrate that our approach outperforms competitive methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-reinforcement">
<titleInfo>
<title>A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Binghui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Cross-lingual stance detection identifies users’ attitudes toward specific targets in texts by transferring knowledge from source languages to target languages. Previous studies have typically facilitated this transfer by translating and aligning labels or targets. However, these methods cannot effectively perform cross-lingual transfer of the complex reasoning processes in stance detection. To address this challenge, we propose a reinforcement learning framework using cross-lingual Chain-of-Thought (CoT) alignment, referred to as RCCA. Specifically, we adopt a cross-lingual CoT alignment strategy to obtain the high-quality CoTs generated from target language inputs. After that, we leverage reinforcement learning by sampling CoTs and assigning rewards according to predefined rules, aiming to enhance the model’s generalization capabilities in the target language. Experimental results on four multilingual datasets demonstrate that our approach outperforms competitive methods.</abstract>
<identifier type="citekey">li-etal-2025-reinforcement</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1115</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1115/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>21674</start>
<end>21688</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought Alignment
%A Li, Binghui
%A Zou, Minghui
%A Zhang, Xiaowang
%A Chen, Shizhan
%A Feng, Zhiyong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F li-etal-2025-reinforcement
%X Cross-lingual stance detection identifies users’ attitudes toward specific targets in texts by transferring knowledge from source languages to target languages. Previous studies have typically facilitated this transfer by translating and aligning labels or targets. However, these methods cannot effectively perform cross-lingual transfer of the complex reasoning processes in stance detection. To address this challenge, we propose a reinforcement learning framework using cross-lingual Chain-of-Thought (CoT) alignment, referred to as RCCA. Specifically, we adopt a cross-lingual CoT alignment strategy to obtain the high-quality CoTs generated from target language inputs. After that, we leverage reinforcement learning by sampling CoTs and assigning rewards according to predefined rules, aiming to enhance the model’s generalization capabilities in the target language. Experimental results on four multilingual datasets demonstrate that our approach outperforms competitive methods.
%R 10.18653/v1/2025.findings-acl.1115
%U https://aclanthology.org/2025.findings-acl.1115/
%U https://doi.org/10.18653/v1/2025.findings-acl.1115
%P 21674-21688
Markdown (Informal)
[A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought Alignment](https://aclanthology.org/2025.findings-acl.1115/) (Li et al., Findings 2025)
ACL