Multi-agent LLMs detect delusion content in audio diaries

Researchers have developed a novel multi-agent language model pipeline to automatically detect and classify delusion-related content in audio diaries. The system, evaluated on transcripts from individuals with persecutory ideation, demonstrated robust performance using a majority voting framework, achieving a Micro F1 score of 0.872 for delusion detection and 0.779 for classification. This approach offers a scalable method for analyzing speech to identify and characterize content suggestive of delusional beliefs. AI

IMPACT Provides a scalable method for automated analysis of speech to identify and characterize content suggestive of delusional beliefs.

RANK_REASON The cluster contains a research paper detailing a novel methodology for detecting specific content in audio diaries using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Multi-Agent Language Models
• Naturalistic Audio Diaries

• paper
• safety
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →