English

Language-Agnostic Suicidal Risk Detection Using Large Language Models

Computation and Language 2025-05-27 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2505.20109,
  title  = {Language-Agnostic Suicidal Risk Detection Using Large Language Models},
  author = {June-Woo Kim and Wonkyo Oh and Haram Yoon and Sung-Hoon Yoon and Dae-Jin Kim and Dong-Ho Lee and Sang-Yeol Lee and Chan-Mo Yang},
  journal= {arXiv preprint arXiv:2505.20109},
  year   = {2025}
}

Comments

Accepted to InterSpeech 2025

R2 v1 2026-07-01T02:39:56.727Z