@inproceedings{antony-schoene-2025-retrieval,
title = "Retrieval-Enhanced Mental Health Assessment: Capturing Self-State Dynamics from Social Media Using In-Context Learning",
author = "Antony, Anson and
Schoene, Annika",
editor = "Zirikly, Ayah and
Yates, Andrew and
Desmet, Bart and
Ireland, Molly and
Bedrick, Steven and
MacAvaney, Sean and
Bar, Kfir and
Ophir, Yaakov",
booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clpsych-1.23/",
doi = "10.18653/v1/2025.clpsych-1.23",
pages = "268--278",
ISBN = "979-8-89176-226-8",
abstract = "This paper presents our approach to the CLPsych 2025 (Tseriotou et al., 2025) shared task, where our proposed system implements a comprehensive solution using In-Context Learning (ICL) with vector similarity to retrieve relevant examples that guide Large Language Models (LLMs) without specific fine-tuning. We leverage ICL to analyze self-states and mental health indicators across three tasks. We developed a pipeline architecture using Ollama, where we are running Llama 3.3 70B locally and specialized vector databases for post- and timeline-level examples. We experimented with different numbers of retrieved examples (k=5 and k=10) to optimize performance. Our results demonstrate the effectiveness of ICL for clinical assessment tasks, particularly when dealing with limited training data in sensitive domains. The system shows strong performance across all tasks, with particular strength in capturing self-state dynamics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antony-schoene-2025-retrieval">
<titleInfo>
<title>Retrieval-Enhanced Mental Health Assessment: Capturing Self-State Dynamics from Social Media Using In-Context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anson</namePart>
<namePart type="family">Antony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Schoene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayah</namePart>
<namePart type="family">Zirikly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Ireland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bedrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">Ophir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-226-8</identifier>
</relatedItem>
<abstract>This paper presents our approach to the CLPsych 2025 (Tseriotou et al., 2025) shared task, where our proposed system implements a comprehensive solution using In-Context Learning (ICL) with vector similarity to retrieve relevant examples that guide Large Language Models (LLMs) without specific fine-tuning. We leverage ICL to analyze self-states and mental health indicators across three tasks. We developed a pipeline architecture using Ollama, where we are running Llama 3.3 70B locally and specialized vector databases for post- and timeline-level examples. We experimented with different numbers of retrieved examples (k=5 and k=10) to optimize performance. Our results demonstrate the effectiveness of ICL for clinical assessment tasks, particularly when dealing with limited training data in sensitive domains. The system shows strong performance across all tasks, with particular strength in capturing self-state dynamics.</abstract>
<identifier type="citekey">antony-schoene-2025-retrieval</identifier>
<identifier type="doi">10.18653/v1/2025.clpsych-1.23</identifier>
<location>
<url>https://aclanthology.org/2025.clpsych-1.23/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>268</start>
<end>278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Enhanced Mental Health Assessment: Capturing Self-State Dynamics from Social Media Using In-Context Learning
%A Antony, Anson
%A Schoene, Annika
%Y Zirikly, Ayah
%Y Yates, Andrew
%Y Desmet, Bart
%Y Ireland, Molly
%Y Bedrick, Steven
%Y MacAvaney, Sean
%Y Bar, Kfir
%Y Ophir, Yaakov
%S Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-226-8
%F antony-schoene-2025-retrieval
%X This paper presents our approach to the CLPsych 2025 (Tseriotou et al., 2025) shared task, where our proposed system implements a comprehensive solution using In-Context Learning (ICL) with vector similarity to retrieve relevant examples that guide Large Language Models (LLMs) without specific fine-tuning. We leverage ICL to analyze self-states and mental health indicators across three tasks. We developed a pipeline architecture using Ollama, where we are running Llama 3.3 70B locally and specialized vector databases for post- and timeline-level examples. We experimented with different numbers of retrieved examples (k=5 and k=10) to optimize performance. Our results demonstrate the effectiveness of ICL for clinical assessment tasks, particularly when dealing with limited training data in sensitive domains. The system shows strong performance across all tasks, with particular strength in capturing self-state dynamics.
%R 10.18653/v1/2025.clpsych-1.23
%U https://aclanthology.org/2025.clpsych-1.23/
%U https://doi.org/10.18653/v1/2025.clpsych-1.23
%P 268-278
Markdown (Informal)
[Retrieval-Enhanced Mental Health Assessment: Capturing Self-State Dynamics from Social Media Using In-Context Learning](https://aclanthology.org/2025.clpsych-1.23/) (Antony & Schoene, CLPsych 2025)
ACL