WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions
Seyedali Mohammadi, Edward Raff, Jinendra Malekar, Vedant Palit, Francis Ferraro, Manas Gaur·June 17, 2024
Summary
This study investigates the use of language models in identifying and explaining Wellness Dimensions (WD) for mental health applications, focusing on models like GPT-3.5/4, MEDALPACA, and RoBERTa. It finds that while general-purpose models like RoBERTa perform better, domain-specific models and LLMs do not significantly improve performance or provide satisfactory explanations. The research highlights the need for more robust and explainable models, especially in mental health, as they often lack domain knowledge and generate inadequate justifications. The study also introduces datasets like MULTIWD and WELLXPLAIN, which emphasize the importance of evaluating models' alignment with expert annotations and their ability to handle complex, real-world mental health contexts.
Introduction
Background
Objective
Method
Data Collection
General-Purpose Models
Domain-Specific Models
Data Preprocessing
Model Evaluation
Experiment Design
Results and Discussion
Model Performance
Limitations and Challenges
Future Directions
Conclusion
Basic info
papers
computation and language
artificial intelligence
Advanced features
Insights
What type of models does the study primarily focus on for identifying Wellness Dimensions in mental health applications?
How do general-purpose models like RoBERTa compare to domain-specific models in the context of this research?
What are the two new datasets introduced in the study that address the limitations of existing models in mental health?
What is the main concern regarding the use of language models in mental health applications, as highlighted by the study?