@inproceedings{park-etal-2026-enhancing-emotional,
title = "Enhancing Emotional Support Conversation with Plug-in Modules for Sequential Strategy Modeling and Strategy-Specialized Generation",
author = "Park, Yerin and
Park, Junhyeok and
Cho, Junsu",
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.1746/",
doi = "10.18653/2026.findings-emnlp.1746",
pages = "37365--37379",
ISBN = "979-8-89176-462-0",
abstract = "Emotional Support Conversation (ESC) aims to alleviate users' emotional distress through multi-turn interactions by selecting appropriate support strategies and generating aligned responses. Despite recent progress, existing approaches face three key limitations: (1) the inability to capture sequential transition patterns of strategies within conversations; (2) a training-inference mismatch in strategy prediction; and (3) reliance on a shared decoder that limits strategy-specific expression. To address these challenges, we propose S3-ESC, a simple framework of three components that are model-agnostic across encoder-decoder ESC backbones. First, we introduce a Sequential strategy predictor that models strategy transition patterns. Second, we apply Scheduled sampling for strategy to mitigate the training-inference mismatch. Third, we propose Selective LoRA for strategy that enables strategy-specialized generation. Experiments on six ESC backbones show that S3-ESC consistently improves strategy prediction accuracy, by up to 4.5pp, while enhancing response quality on most of them. Our code is publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-enhancing-emotional">
<titleInfo>
<title>Enhancing Emotional Support Conversation with Plug-in Modules for Sequential Strategy Modeling and Strategy-Specialized Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yerin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhyeok</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junsu</namePart>
<namePart type="family">Cho</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>Emotional Support Conversation (ESC) aims to alleviate users’ emotional distress through multi-turn interactions by selecting appropriate support strategies and generating aligned responses. Despite recent progress, existing approaches face three key limitations: (1) the inability to capture sequential transition patterns of strategies within conversations; (2) a training-inference mismatch in strategy prediction; and (3) reliance on a shared decoder that limits strategy-specific expression. To address these challenges, we propose S3-ESC, a simple framework of three components that are model-agnostic across encoder-decoder ESC backbones. First, we introduce a Sequential strategy predictor that models strategy transition patterns. Second, we apply Scheduled sampling for strategy to mitigate the training-inference mismatch. Third, we propose Selective LoRA for strategy that enables strategy-specialized generation. Experiments on six ESC backbones show that S3-ESC consistently improves strategy prediction accuracy, by up to 4.5pp, while enhancing response quality on most of them. Our code is publicly available.</abstract>
<identifier type="citekey">park-etal-2026-enhancing-emotional</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1746</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1746/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37365</start>
<end>37379</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Emotional Support Conversation with Plug-in Modules for Sequential Strategy Modeling and Strategy-Specialized Generation
%A Park, Yerin
%A Park, Junhyeok
%A Cho, Junsu
%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 park-etal-2026-enhancing-emotional
%X Emotional Support Conversation (ESC) aims to alleviate users’ emotional distress through multi-turn interactions by selecting appropriate support strategies and generating aligned responses. Despite recent progress, existing approaches face three key limitations: (1) the inability to capture sequential transition patterns of strategies within conversations; (2) a training-inference mismatch in strategy prediction; and (3) reliance on a shared decoder that limits strategy-specific expression. To address these challenges, we propose S3-ESC, a simple framework of three components that are model-agnostic across encoder-decoder ESC backbones. First, we introduce a Sequential strategy predictor that models strategy transition patterns. Second, we apply Scheduled sampling for strategy to mitigate the training-inference mismatch. Third, we propose Selective LoRA for strategy that enables strategy-specialized generation. Experiments on six ESC backbones show that S3-ESC consistently improves strategy prediction accuracy, by up to 4.5pp, while enhancing response quality on most of them. Our code is publicly available.
%R 10.18653/2026.findings-emnlp.1746
%U https://aclanthology.org/2026.findings-emnlp.1746/
%U https://doi.org/10.18653/2026.findings-emnlp.1746
%P 37365-37379
Markdown (Informal)
[Enhancing Emotional Support Conversation with Plug-in Modules for Sequential Strategy Modeling and Strategy-Specialized Generation](https://aclanthology.org/2026.findings-emnlp.1746/) (Park et al., Findings 2026)
ACL