<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2026-beyond">
    <titleInfo>
        <title>Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuqi</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lizi</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinggui</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Boyang</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richang</namePart>
        <namePart type="family">Hong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Emotional support conversation systems strive to emulate the empathetic depth of human therapists, yet current approaches often fail due to the “Cognitive Gap”—the inability to discern the latent psychological evaluations driving a user’s distress. Existing retrieval-augmented generation paradigms exacerbate this by relying on semantic similarity, frequently retrieving historical dialogues that are surface analogous but therapeutically incongruent. To bridge this gap, we introduce Appraisal-Guided Chain-of-Thought Reasoning &amp; Retrieval (AG-CTR²) for better emotional support. Specifically, we bootstrap the MLLM to generate appraisal-guided reasoning chains and apply a dual-signal verification mechanism using ground-truth emotion labels and a teacher model to verify and correct them. Under such instance-level guidance, we finetune the MLLM to internalize such reasoning capability. At inference, the model utilizes its generated appraisal chain as a structured query to help retrieve historical therapeutic responses based on psychological situation similarity rather than content surface proximity. Extensive experiments and analyses on two ESC benchmarks demonstrate that AG-CTR² significantly outperforms state-of-the-art baselines.</abstract>
    <identifier type="citekey">chu-etal-2026-beyond</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.844/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>17104</start>
            <end>17119</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations
%A Chu, Yuqi
%A Liao, Lizi
%A Liang, Jinggui
%A Li, Boyang
%A Hong, Richang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F chu-etal-2026-beyond
%X Emotional support conversation systems strive to emulate the empathetic depth of human therapists, yet current approaches often fail due to the “Cognitive Gap”—the inability to discern the latent psychological evaluations driving a user’s distress. Existing retrieval-augmented generation paradigms exacerbate this by relying on semantic similarity, frequently retrieving historical dialogues that are surface analogous but therapeutically incongruent. To bridge this gap, we introduce Appraisal-Guided Chain-of-Thought Reasoning & Retrieval (AG-CTR²) for better emotional support. Specifically, we bootstrap the MLLM to generate appraisal-guided reasoning chains and apply a dual-signal verification mechanism using ground-truth emotion labels and a teacher model to verify and correct them. Under such instance-level guidance, we finetune the MLLM to internalize such reasoning capability. At inference, the model utilizes its generated appraisal chain as a structured query to help retrieve historical therapeutic responses based on psychological situation similarity rather than content surface proximity. Extensive experiments and analyses on two ESC benchmarks demonstrate that AG-CTR² significantly outperforms state-of-the-art baselines.
%U https://aclanthology.org/2026.findings-acl.844/
%P 17104-17119

Markdown (Informal)

[Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations](https://aclanthology.org/2026.findings-acl.844/) (Chu et al., Findings 2026)

• Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (Chu et al., Findings 2026)

ACL

• Yuqi Chu, Lizi Liao, Jinggui Liang, Boyang Li, and Richang Hong. 2026. Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations. In Findings of the Association for Computational Linguistics: ACL 2026, pages 17104–17119, San Diego, California, United States. Association for Computational Linguistics.