@inproceedings{nguyen-etal-2026-reframe,
title = "Reframe to Retrieve: Cognition-aware {RAG} with Projections Inspired by Appraisal and {CBT} for Conversational Mental Health Support",
author = "Nguyen, Minh-Tien and
Le, Huu-Loi and
Phan, Manh-Cuong and
Le, Duong-Hieu and
Pham, Dinh-Phuc and
Nguyen, Van-Quyet and
Hotta, Hajime",
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.658/",
pages = "13800--13822",
ISBN = "979-8-89176-462-0",
abstract = "This paper introduces **CogRAG**, a new RAG pipeline, for conversational mental health support. Different from conventional RAG that is usually optimized for semantic relevance, CogRAG integrates cognitive factors into both retrieval and response generation stages. To do that, CogRAG uses projections by Appraisal-Theory- and CBT-inspired prompts that are applied symmetrically to patient queries and therapist responses, bridging their lexical asymmetry for retrieval. To deal with crisis cases, it augments safety-planning cards from data that guide generation to follow therapies. Experimental results on two datasets show that cognitive modeling helps improve retrieval and generation performance; gains are most pronounced in counseling quality, while safety-related improvements are modest but consistent. We do not claim to implement clinical CBT or to recover ground-truth cognitive states (Code and data: https://github.com/Cog-AI-Lab/CogRAG)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-reframe">
<titleInfo>
<title>Reframe to Retrieve: Cognition-aware RAG with Projections Inspired by Appraisal and CBT for Conversational Mental Health Support</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh-Tien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huu-Loi</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manh-Cuong</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duong-Hieu</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinh-Phuc</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Van-Quyet</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajime</namePart>
<namePart type="family">Hotta</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>This paper introduces **CogRAG**, a new RAG pipeline, for conversational mental health support. Different from conventional RAG that is usually optimized for semantic relevance, CogRAG integrates cognitive factors into both retrieval and response generation stages. To do that, CogRAG uses projections by Appraisal-Theory- and CBT-inspired prompts that are applied symmetrically to patient queries and therapist responses, bridging their lexical asymmetry for retrieval. To deal with crisis cases, it augments safety-planning cards from data that guide generation to follow therapies. Experimental results on two datasets show that cognitive modeling helps improve retrieval and generation performance; gains are most pronounced in counseling quality, while safety-related improvements are modest but consistent. We do not claim to implement clinical CBT or to recover ground-truth cognitive states (Code and data: https://github.com/Cog-AI-Lab/CogRAG).</abstract>
<identifier type="citekey">nguyen-etal-2026-reframe</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.658/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>13800</start>
<end>13822</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reframe to Retrieve: Cognition-aware RAG with Projections Inspired by Appraisal and CBT for Conversational Mental Health Support
%A Nguyen, Minh-Tien
%A Le, Huu-Loi
%A Phan, Manh-Cuong
%A Le, Duong-Hieu
%A Pham, Dinh-Phuc
%A Nguyen, Van-Quyet
%A Hotta, Hajime
%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 nguyen-etal-2026-reframe
%X This paper introduces **CogRAG**, a new RAG pipeline, for conversational mental health support. Different from conventional RAG that is usually optimized for semantic relevance, CogRAG integrates cognitive factors into both retrieval and response generation stages. To do that, CogRAG uses projections by Appraisal-Theory- and CBT-inspired prompts that are applied symmetrically to patient queries and therapist responses, bridging their lexical asymmetry for retrieval. To deal with crisis cases, it augments safety-planning cards from data that guide generation to follow therapies. Experimental results on two datasets show that cognitive modeling helps improve retrieval and generation performance; gains are most pronounced in counseling quality, while safety-related improvements are modest but consistent. We do not claim to implement clinical CBT or to recover ground-truth cognitive states (Code and data: https://github.com/Cog-AI-Lab/CogRAG).
%U https://aclanthology.org/2026.findings-emnlp.658/
%P 13800-13822
Markdown (Informal)
[Reframe to Retrieve: Cognition-aware RAG with Projections Inspired by Appraisal and CBT for Conversational Mental Health Support](https://aclanthology.org/2026.findings-emnlp.658/) (Nguyen et al., Findings 2026)
ACL