Guardado en:
Detalles Bibliográficos
Autores principales: Kim, June-Woo, Oh, Wonkyo, Yoon, Haram, Yoon, Sung-Hoon, Kim, Dae-Jin, Lee, Dong-Ho, Lee, Sang-Yeol, Yang, Chan-Mo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.20109
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910968914640896
author Kim, June-Woo
Oh, Wonkyo
Yoon, Haram
Yoon, Sung-Hoon
Kim, Dae-Jin
Lee, Dong-Ho
Lee, Sang-Yeol
Yang, Chan-Mo
author_facet Kim, June-Woo
Oh, Wonkyo
Yoon, Haram
Yoon, Sung-Hoon
Kim, Dae-Jin
Lee, Dong-Ho
Lee, Sang-Yeol
Yang, Chan-Mo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Language-Agnostic Suicidal Risk Detection Using Large Language Models
Kim, June-Woo
Oh, Wonkyo
Yoon, Haram
Yoon, Sung-Hoon
Kim, Dae-Jin
Lee, Dong-Ho
Lee, Sang-Yeol
Yang, Chan-Mo
Computation and Language
Artificial Intelligence
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.
title Language-Agnostic Suicidal Risk Detection Using Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.20109