Prompt-based learning and its application in mental health
Prompt-based learning and its application in mental health
With the rise of large language models (LLMs), prompt-based learning has become a widely studied and essential topic in the field of Natural Language Processing (NLP). Due to their impressive performance in zero-shot and few-shot settings, prompting offers a strong opportunity for low-resource domains such as mental health. Mental health is a prevalent global concern, with increasing numbers of users sharing their experiences on social media. However, data from these platforms is often complex, and manual annotation at scale is both time-consuming and costly.
This thesis investigates the central hypothesis that task-specific and well-designed prompt strategies are essential for effectively adapting LLMs to low-resource domains, with a particular focus on mental health applications.
This study systematically examines the role of prompt position across tasks and prompting methods, revealing that position significantly affects model performance and is often overlooked in prior work. A domain-specific prompting method is then explored to extract and summarise evidence of suicidal ideation with minimal supervision. Finally, a novel LLM-based framework is developed for multi-label life event annotation in the mental health domain, incorporating tailored prompting techniques and prompt position self-ordering to enable effective automatic annotation.
University of Southampton
Mao, Junyu
dde288a4-c7c9-423b-8271-e1b5d7a2d675
2025
Mao, Junyu
dde288a4-c7c9-423b-8271-e1b5d7a2d675
Middleton, Stuart
404b62ba-d77e-476b-9775-32645b04473f
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Mao, Junyu
(2025)
Prompt-based learning and its application in mental health.
University of Southampton, Doctoral Thesis, 155pp.
Record type:
Thesis
(Doctoral)
Abstract
With the rise of large language models (LLMs), prompt-based learning has become a widely studied and essential topic in the field of Natural Language Processing (NLP). Due to their impressive performance in zero-shot and few-shot settings, prompting offers a strong opportunity for low-resource domains such as mental health. Mental health is a prevalent global concern, with increasing numbers of users sharing their experiences on social media. However, data from these platforms is often complex, and manual annotation at scale is both time-consuming and costly.
This thesis investigates the central hypothesis that task-specific and well-designed prompt strategies are essential for effectively adapting LLMs to low-resource domains, with a particular focus on mental health applications.
This study systematically examines the role of prompt position across tasks and prompting methods, revealing that position significantly affects model performance and is often overlooked in prior work. A domain-specific prompting method is then explored to extract and summarise evidence of suicidal ideation with minimal supervision. Finally, a novel LLM-based framework is developed for multi-label life event annotation in the mental health domain, incorporating tailored prompting techniques and prompt position self-ordering to enable effective automatic annotation.
Text
Final-thesis-submission-Examination-Miss-Junyu-Mao
Restricted to Repository staff only
More information
Published date: 2025
Identifiers
Local EPrints ID: 505273
URI: http://eprints.soton.ac.uk/id/eprint/505273
PURE UUID: e411b58c-a25c-45b7-9915-6c2f44a33c48
Catalogue record
Date deposited: 03 Oct 2025 16:33
Last modified: 04 Oct 2025 02:04
Export record
Contributors
Author:
Junyu Mao
Thesis advisor:
Mahesan Niranjan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics