Summary of Still Not Quite There! Evaluating Large Language Models For Comorbid Mental Health Diagnosis, by Amey Hengle et al.
Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis
by Amey Hengle, Atharva Kulkarni, Shantanu Patankar, Madhumitha Chandrasekaran, Sneha D’Silva, Jemima Jacob, Rashmi Gupta
First submitted to arxiv on: 4 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study introduces ANGST, a novel benchmark for depression-anxiety comorbidity classification from social media posts. Unlike existing datasets that oversimplify the interplay between mental health disorders, ANGST enables multi-label classification, allowing each post to be identified as indicating both depression and/or anxiety. The dataset comprises 2876 expert-annotated posts and an additional 7667 silver-labeled posts, providing a more representative sample of online mental health discourse. State-of-the-art language models, including Mental-BERT and GPT-4, were benchmarked against ANGST, revealing significant insights into their capabilities and limitations in complex diagnostic scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study creates a new way to understand depression and anxiety from social media posts. It’s called ANGST, and it helps experts identify when someone is talking about both depression and anxiety at the same time. The dataset has 2876 expert-annotated posts and another 7667 posts that were labeled by other people. This study also tests how well language models like Mental-BERT and GPT-4 can understand these complex mental health issues. |
Keywords
» Artificial intelligence » Bert » Classification » Discourse » Gpt
