@inproceedings{wen-etal-2025-listen,
title = "Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation",
author = "Wen, Zhuofan and
Lian, Zheng and
Chen, Shun and
Yao, Hailiang and
Yang, Longjiang and
Liu, Bin and
Tao, Jianhua",
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.590/",
doi = "10.18653/v1/2025.findings-acl.590",
pages = "11313--11327",
ISBN = "979-8-89176-256-5",
abstract = "The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional perception often leads to inconsistent annotations, limiting the robustness of current models. Addressing these challenges requires more fine-grained methods and evaluation frameworks. In this paper, we propose the Retrieval-Augmented Emotion Reasoning (RAER) framework, a plug-and-play module that enhances MLLMs' ability to tackle compound and context-rich emotion tasks. To systematically evaluate model performance, we introduce the Stimulus-Armed Bandit (SAB) framework, designed to benchmark emotional reasoning capabilities. Additionally, we construct the Compound Emotion QA dataset, an AI-generated multimodal dataset aimed at strengthening emotion understanding in MLLMs. Experimental results demonstrate the effectiveness of RAER across both traditional benchmarks and SAB evaluations, highlighting its potential to enhance emotional intelligence in multimodal AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wen-etal-2025-listen">
<titleInfo>
<title>Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuofan</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailiang</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longjiang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhua</namePart>
<namePart type="family">Tao</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>The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional perception often leads to inconsistent annotations, limiting the robustness of current models. Addressing these challenges requires more fine-grained methods and evaluation frameworks. In this paper, we propose the Retrieval-Augmented Emotion Reasoning (RAER) framework, a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks. To systematically evaluate model performance, we introduce the Stimulus-Armed Bandit (SAB) framework, designed to benchmark emotional reasoning capabilities. Additionally, we construct the Compound Emotion QA dataset, an AI-generated multimodal dataset aimed at strengthening emotion understanding in MLLMs. Experimental results demonstrate the effectiveness of RAER across both traditional benchmarks and SAB evaluations, highlighting its potential to enhance emotional intelligence in multimodal AI systems.</abstract>
<identifier type="citekey">wen-etal-2025-listen</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.590</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.590/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>11313</start>
<end>11327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation
%A Wen, Zhuofan
%A Lian, Zheng
%A Chen, Shun
%A Yao, Hailiang
%A Yang, Longjiang
%A Liu, Bin
%A Tao, Jianhua
%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 wen-etal-2025-listen
%X The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional perception often leads to inconsistent annotations, limiting the robustness of current models. Addressing these challenges requires more fine-grained methods and evaluation frameworks. In this paper, we propose the Retrieval-Augmented Emotion Reasoning (RAER) framework, a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks. To systematically evaluate model performance, we introduce the Stimulus-Armed Bandit (SAB) framework, designed to benchmark emotional reasoning capabilities. Additionally, we construct the Compound Emotion QA dataset, an AI-generated multimodal dataset aimed at strengthening emotion understanding in MLLMs. Experimental results demonstrate the effectiveness of RAER across both traditional benchmarks and SAB evaluations, highlighting its potential to enhance emotional intelligence in multimodal AI systems.
%R 10.18653/v1/2025.findings-acl.590
%U https://aclanthology.org/2025.findings-acl.590/
%U https://doi.org/10.18653/v1/2025.findings-acl.590
%P 11313-11327
Markdown (Informal)
[Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation](https://aclanthology.org/2025.findings-acl.590/) (Wen et al., Findings 2025)
ACL
- Zhuofan Wen, Zheng Lian, Shun Chen, Hailiang Yao, Longjiang Yang, Bin Liu, and Jianhua Tao. 2025. Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11313–11327, Vienna, Austria. Association for Computational Linguistics.