A Dual-Prompting for Interpretable Mental Health Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917595989409792 |
|---|---|
| author | Jeon, Hyolim Yoo, Dongje Lee, Daeun Son, Sejung Kim, Seungbae Han, Jinyoung |
| author_facet | Jeon, Hyolim Yoo, Dongje Lee, Daeun Son, Sejung Kim, Seungbae Han, Jinyoung |
| contents | Despite the increasing demand for AI-based mental health monitoring tools, their practical utility for clinicians is limited by the lack of interpretability.The CLPsych 2024 Shared Task (Chim et al., 2024) aims to enhance the interpretability of Large Language Models (LLMs), particularly in mental health analysis, by providing evidence of suicidality through linguistic content. We propose a dual-prompting approach: (i) Knowledge-aware evidence extraction by leveraging the expert identity and a suicide dictionary with a mental health-specific LLM; and (ii) Evidence summarization by employing an LLM-based consistency evaluator. Comprehensive experiments demonstrate the effectiveness of combining domain-specific information, revealing performance improvements and the approach's potential to aid clinicians in assessing mental state progression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Dual-Prompting for Interpretable Mental Health Language Models Jeon, Hyolim Yoo, Dongje Lee, Daeun Son, Sejung Kim, Seungbae Han, Jinyoung Computation and Language Artificial Intelligence Despite the increasing demand for AI-based mental health monitoring tools, their practical utility for clinicians is limited by the lack of interpretability.The CLPsych 2024 Shared Task (Chim et al., 2024) aims to enhance the interpretability of Large Language Models (LLMs), particularly in mental health analysis, by providing evidence of suicidality through linguistic content. We propose a dual-prompting approach: (i) Knowledge-aware evidence extraction by leveraging the expert identity and a suicide dictionary with a mental health-specific LLM; and (ii) Evidence summarization by employing an LLM-based consistency evaluator. Comprehensive experiments demonstrate the effectiveness of combining domain-specific information, revealing performance improvements and the approach's potential to aid clinicians in assessing mental state progression. |
| title | A Dual-Prompting for Interpretable Mental Health Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.14854 |