Evidence-Driven Marker Extraction for Social Media Suicide Risk Detection

TL;DR

This paper presents ED-LLM, a multi-task learning approach using Mistral-7B to improve interpretability and efficiency in social media-based suicide risk detection by explicitly extracting clinical markers and classifying risk levels.

Contribution

Introduction of ED-LLM, a novel multi-task learning framework that enhances interpretability and performance in suicide risk detection from social media texts.

Findings

ED-LLM outperforms baselines in clinical marker span identification.

ED-LLM achieves competitive accuracy in suicide risk classification.

The evidence-driven approach improves interpretability of risk assessments.

Abstract

Early detection of suicide risk from social media text is crucial for timely intervention. While Large Language Models (LLMs) offer promising capabilities in this domain, challenges remain in terms of interpretability and computational efficiency. This paper introduces Evidence-Driven LLM (ED-LLM), a novel approach for clinical marker extraction and suicide risk classification. ED-LLM employs a multi-task learning framework, jointly training a Mistral-7B based model to identify clinical marker spans and classify suicide risk levels. This evidence-driven strategy enhances interpretability by explicitly highlighting textual evidence supporting risk assessments. Evaluated on the CLPsych datasets, ED-LLM demonstrates competitive performance in risk classification and superior capability in clinical marker span identification compared to baselines including fine-tuned LLMs, traditional machine learning, and prompt-based methods. The results highlight the effectiveness of multi-task learning for interpretable and efficient LLM-based suicide risk assessment, paving the way for clinically relevant applications.