@inproceedings{zeng-etal-2026-expcsd,
title = "{E}xp{CSD}: Experience-based Debiasing Framework for Conversational Stance Detection Grounded in Latent Thinking Paths",
author = "Zeng, Xiang and
Wang, Ye and
Song, Xin and
Zhu, Dong and
Hou, Wenqing and
Zhou, Bin",
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.2286/",
pages = "48998--49015",
ISBN = "979-8-89176-462-0",
abstract = "Conversational stance detection, which aims to identify users' attitudes in conversation threads, has attracted increasing attention in recent years. Yet, mainstream LLM-based approaches remain prone to biases caused by spurious correlations. Existing debiasing methods either rely on indiscriminate multi-step prompting, which can induce unnecessary reasoning and overthinking, or require expensive fine-tuning on curated data. To address these challenges, we propose ExpCSD, an experience-based debiasing framework grounded in latent thinking paths that follows a debias-only-when-needed principle. ExpCSD first assesses whether an LLM{'}s latent thinking path is biased and selectively retrieves and injects historically similar debiasing experiences only when necessary, without updating model parameters. Experiments on public benchmarks show that ExpCSD outperforms strong baselines in stance detection accuracy while avoiding overthinking and costly fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2026-expcsd">
<titleInfo>
<title>ExpCSD: Experience-based Debiasing Framework for Conversational Stance Detection Grounded in Latent Thinking Paths</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqing</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Zhou</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>Conversational stance detection, which aims to identify users’ attitudes in conversation threads, has attracted increasing attention in recent years. Yet, mainstream LLM-based approaches remain prone to biases caused by spurious correlations. Existing debiasing methods either rely on indiscriminate multi-step prompting, which can induce unnecessary reasoning and overthinking, or require expensive fine-tuning on curated data. To address these challenges, we propose ExpCSD, an experience-based debiasing framework grounded in latent thinking paths that follows a debias-only-when-needed principle. ExpCSD first assesses whether an LLM’s latent thinking path is biased and selectively retrieves and injects historically similar debiasing experiences only when necessary, without updating model parameters. Experiments on public benchmarks show that ExpCSD outperforms strong baselines in stance detection accuracy while avoiding overthinking and costly fine-tuning.</abstract>
<identifier type="citekey">zeng-etal-2026-expcsd</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2286/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>48998</start>
<end>49015</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExpCSD: Experience-based Debiasing Framework for Conversational Stance Detection Grounded in Latent Thinking Paths
%A Zeng, Xiang
%A Wang, Ye
%A Song, Xin
%A Zhu, Dong
%A Hou, Wenqing
%A Zhou, Bin
%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 zeng-etal-2026-expcsd
%X Conversational stance detection, which aims to identify users’ attitudes in conversation threads, has attracted increasing attention in recent years. Yet, mainstream LLM-based approaches remain prone to biases caused by spurious correlations. Existing debiasing methods either rely on indiscriminate multi-step prompting, which can induce unnecessary reasoning and overthinking, or require expensive fine-tuning on curated data. To address these challenges, we propose ExpCSD, an experience-based debiasing framework grounded in latent thinking paths that follows a debias-only-when-needed principle. ExpCSD first assesses whether an LLM’s latent thinking path is biased and selectively retrieves and injects historically similar debiasing experiences only when necessary, without updating model parameters. Experiments on public benchmarks show that ExpCSD outperforms strong baselines in stance detection accuracy while avoiding overthinking and costly fine-tuning.
%U https://aclanthology.org/2026.findings-emnlp.2286/
%P 48998-49015
Markdown (Informal)
[ExpCSD: Experience-based Debiasing Framework for Conversational Stance Detection Grounded in Latent Thinking Paths](https://aclanthology.org/2026.findings-emnlp.2286/) (Zeng et al., Findings 2026)
ACL