@inproceedings{yin-etal-2026-fine,
title = "Fine-grained stance cues and commonsense knowledge Integrated Reasoning Enhancement for Zero-shot Conversational Stance Detection",
author = "Yin, Weiming and
Ning, Jinzhong and
Zhang, Yijia and
Sun, Yuanyuan",
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.603/",
doi = "10.18653/2026.findings-emnlp.603",
pages = "12723--12747",
ISBN = "979-8-89176-462-0",
abstract = "Conversational stance detection aims to identify a speaker{'}s attitude toward a target in multi-turn dialogues, while the zero-shot setting requires generalization to unseen targets. Existing methods often rely on coarse-grained semantic representations or static knowledge injection, limiting their ability to capture subtle stance cues and utilize commonsense knowledge. To address this, we propose FIRE, a reasoning-enhanced framework that integrates fine-grained stance cues and commonsense knowledge for zero-shot conversational stance detection. FIRE adaptively mines sentiment, rhetorical, referential, cross-turn stance dependency cues and commonsense knowledge, and fuses them into explicit reasoning chains for target-aware stance inference. By combining supervised instruction tuning with reinforcement learning, FIRE further improves reasoning-chain quality and stance prediction. Experiments on benchmark datasets show that FIRE consistently outperforms strong baselines across different target types and LLM backbones, demonstrating the effectiveness of fine-grained cue modeling and knowledge-driven reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2026-fine">
<titleInfo>
<title>Fine-grained stance cues and commonsense knowledge Integrated Reasoning Enhancement for Zero-shot Conversational Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiming</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinzhong</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijia</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanyuan</namePart>
<namePart type="family">Sun</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 aims to identify a speaker’s attitude toward a target in multi-turn dialogues, while the zero-shot setting requires generalization to unseen targets. Existing methods often rely on coarse-grained semantic representations or static knowledge injection, limiting their ability to capture subtle stance cues and utilize commonsense knowledge. To address this, we propose FIRE, a reasoning-enhanced framework that integrates fine-grained stance cues and commonsense knowledge for zero-shot conversational stance detection. FIRE adaptively mines sentiment, rhetorical, referential, cross-turn stance dependency cues and commonsense knowledge, and fuses them into explicit reasoning chains for target-aware stance inference. By combining supervised instruction tuning with reinforcement learning, FIRE further improves reasoning-chain quality and stance prediction. Experiments on benchmark datasets show that FIRE consistently outperforms strong baselines across different target types and LLM backbones, demonstrating the effectiveness of fine-grained cue modeling and knowledge-driven reasoning.</abstract>
<identifier type="citekey">yin-etal-2026-fine</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.603</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.603/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12723</start>
<end>12747</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-grained stance cues and commonsense knowledge Integrated Reasoning Enhancement for Zero-shot Conversational Stance Detection
%A Yin, Weiming
%A Ning, Jinzhong
%A Zhang, Yijia
%A Sun, Yuanyuan
%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 yin-etal-2026-fine
%X Conversational stance detection aims to identify a speaker’s attitude toward a target in multi-turn dialogues, while the zero-shot setting requires generalization to unseen targets. Existing methods often rely on coarse-grained semantic representations or static knowledge injection, limiting their ability to capture subtle stance cues and utilize commonsense knowledge. To address this, we propose FIRE, a reasoning-enhanced framework that integrates fine-grained stance cues and commonsense knowledge for zero-shot conversational stance detection. FIRE adaptively mines sentiment, rhetorical, referential, cross-turn stance dependency cues and commonsense knowledge, and fuses them into explicit reasoning chains for target-aware stance inference. By combining supervised instruction tuning with reinforcement learning, FIRE further improves reasoning-chain quality and stance prediction. Experiments on benchmark datasets show that FIRE consistently outperforms strong baselines across different target types and LLM backbones, demonstrating the effectiveness of fine-grained cue modeling and knowledge-driven reasoning.
%R 10.18653/2026.findings-emnlp.603
%U https://aclanthology.org/2026.findings-emnlp.603/
%U https://doi.org/10.18653/2026.findings-emnlp.603
%P 12723-12747
Markdown (Informal)
[Fine-grained stance cues and commonsense knowledge Integrated Reasoning Enhancement for Zero-shot Conversational Stance Detection](https://aclanthology.org/2026.findings-emnlp.603/) (Yin et al., Findings 2026)
ACL