Veterans' Mental Health Crisis Severity Annotation: Do LLMs Agree More Than Human Experts?
arXiv cs.AI · K M Sajjadul Islam, Pranav Yaramalla, Nadiyah Johnson, Mark Flower, Praveen Madiraju, Zeno Franco ·
arXiv:2611.10048v1 Announce Type: new Abstract: Large language models (LLMs) offer a scalable approach for annotating mental health and crisis-related social media content, but their reliability in safety-critical tasks remains unclear. This study evaluates LLM-based crisis-severity annotation of veteran-related…
Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.
Read the full story on arXiv cs.AI
Related coverage
Google AI Blog · 5h ago
Google Cloud launches Gemini for healthcare.
arXiv cs.AI · 13h ago
Generative Active Learning for Label-Efficient Pan-Organ Ultrasound Diagnosis
arXiv cs.AI · 13h ago
Adversarial Evaluation of Large Language Models for Patient-Friendly Radiology Report Summarization
WCAX · 21h ago
Vermont hospitals embrace AI as questions about oversight remain