@inproceedings{singh-etal-2024-deciphering,
title = "Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal {LLM}-Based Detection and Reasoning Framework",
author = "Singh, Gopendra and
Vemulapalli, Sai and
Firdaus, Mauajama and
Ekbal, Asif",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1256",
pages = "22546--22570",
abstract = "Cognitive distortion research holds increasing significance as it sheds light on pervasive errors in thinking patterns, providing crucial insights into mental health challenges and fostering the development of targeted interventions and therapies. This paper delves into the complex domain of cognitive distortions which are prevalent distortions in cognitive processes often associated with mental health issues. Focusing on patient-doctor dialogues, we introduce a pioneering method for detecting and reasoning about cognitive distortions utilizing Large Language Models (LLMs). Operating within a multimodal context encompassing audio, video, and textual data, our approach underscores the critical importance of integrating diverse modalities for a comprehensive understanding of cognitive distortions. By leveraging multimodal information, including audio, video, and textual data, our method offers a nuanced perspective that enhances the accuracy and depth of cognitive distortion detection and reasoning in a zero-shot manner. Our proposed hierarchical framework adeptly tackles both detection and reasoning tasks, showcasing significant performance enhancements compared to current methodologies. Through comprehensive analysis, we elucidate the efficacy of our approach, offering promising insights into the diagnosis and understanding of cognitive distortions in multimodal settings.The code and dataset can be found here: \url{https://github.com/clang1234/ZS-CoDR.git}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2024-deciphering">
<titleInfo>
<title>Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gopendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="family">Vemulapalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauajama</namePart>
<namePart type="family">Firdaus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cognitive distortion research holds increasing significance as it sheds light on pervasive errors in thinking patterns, providing crucial insights into mental health challenges and fostering the development of targeted interventions and therapies. This paper delves into the complex domain of cognitive distortions which are prevalent distortions in cognitive processes often associated with mental health issues. Focusing on patient-doctor dialogues, we introduce a pioneering method for detecting and reasoning about cognitive distortions utilizing Large Language Models (LLMs). Operating within a multimodal context encompassing audio, video, and textual data, our approach underscores the critical importance of integrating diverse modalities for a comprehensive understanding of cognitive distortions. By leveraging multimodal information, including audio, video, and textual data, our method offers a nuanced perspective that enhances the accuracy and depth of cognitive distortion detection and reasoning in a zero-shot manner. Our proposed hierarchical framework adeptly tackles both detection and reasoning tasks, showcasing significant performance enhancements compared to current methodologies. Through comprehensive analysis, we elucidate the efficacy of our approach, offering promising insights into the diagnosis and understanding of cognitive distortions in multimodal settings.The code and dataset can be found here: https://github.com/clang1234/ZS-CoDR.git</abstract>
<identifier type="citekey">singh-etal-2024-deciphering</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1256</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>22546</start>
<end>22570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework
%A Singh, Gopendra
%A Vemulapalli, Sai
%A Firdaus, Mauajama
%A Ekbal, Asif
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F singh-etal-2024-deciphering
%X Cognitive distortion research holds increasing significance as it sheds light on pervasive errors in thinking patterns, providing crucial insights into mental health challenges and fostering the development of targeted interventions and therapies. This paper delves into the complex domain of cognitive distortions which are prevalent distortions in cognitive processes often associated with mental health issues. Focusing on patient-doctor dialogues, we introduce a pioneering method for detecting and reasoning about cognitive distortions utilizing Large Language Models (LLMs). Operating within a multimodal context encompassing audio, video, and textual data, our approach underscores the critical importance of integrating diverse modalities for a comprehensive understanding of cognitive distortions. By leveraging multimodal information, including audio, video, and textual data, our method offers a nuanced perspective that enhances the accuracy and depth of cognitive distortion detection and reasoning in a zero-shot manner. Our proposed hierarchical framework adeptly tackles both detection and reasoning tasks, showcasing significant performance enhancements compared to current methodologies. Through comprehensive analysis, we elucidate the efficacy of our approach, offering promising insights into the diagnosis and understanding of cognitive distortions in multimodal settings.The code and dataset can be found here: https://github.com/clang1234/ZS-CoDR.git
%U https://aclanthology.org/2024.emnlp-main.1256
%P 22546-22570
Markdown (Informal)
[Deciphering Cognitive Distortions in Patient-Doctor Mental Health Conversations: A Multimodal LLM-Based Detection and Reasoning Framework](https://aclanthology.org/2024.emnlp-main.1256) (Singh et al., EMNLP 2024)
ACL