Language-Agnostic Suicidal Risk Detection Using Large Language Models

TL;DR

This paper presents a language-agnostic framework for suicidal risk detection using large language models, enabling cross-linguistic analysis and overcoming language-specific limitations in existing methods.

Contribution

The study introduces a novel approach that leverages LLMs with prompt-based queries for language-agnostic suicidal risk assessment, enhancing scalability and robustness.

Findings

Performance comparable to direct fine-tuning methods

Effective cross-linguistic analysis with Chinese and English

Potential to overcome language constraints in risk detection

Abstract

Suicidal risk detection in adolescents is a critical challenge, yet existing methods rely on language-specific models, limiting scalability and generalization. This study introduces a novel language-agnostic framework for suicidal risk assessment with large language models (LLMs). We generate Chinese transcripts from speech using an ASR model and then employ LLMs with prompt-based queries to extract suicidal risk-related features from these transcripts. The extracted features are retained in both Chinese and English to enable cross-linguistic analysis and then used to fine-tune corresponding pretrained language models independently. Experimental results show that our method achieves performance comparable to direct fine-tuning with ASR results or to models trained solely on Chinese suicidal risk-related features, demonstrating its potential to overcome language constraints and improve the robustness of suicidal risk assessment.