This paper is in the following e-collection/theme issue:

Natural Language Processing (935) Depression and Mood Disorders; Suicide Prevention (1730) Misinformation and Disinformation Outbreaks and Information Prevalence Studies (99) Applications of AI (313) Infoveillance, Infodemiology, Digital Disease Surveillance, Infodemic Management (1150) Mental Health Surveillance and Epidemiology (99)

Published on in Vol 14 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/73725, first published .
Iterative Large Language Model–Guided Sampling and Expert-Annotated Benchmark Corpus for Harmful Suicide Content Detection: Development and Validation Study

Iterative Large Language Model–Guided Sampling and Expert-Annotated Benchmark Corpus for Harmful Suicide Content Detection: Development and Validation Study

Iterative Large Language Model–Guided Sampling and Expert-Annotated Benchmark Corpus for Harmful Suicide Content Detection: Development and Validation Study

Authors of this article:

Kyumin Park1 Author Orcid Image ;   Myung Jae Baik2 Author Orcid Image ;   YeongJun Hwang3 Author Orcid Image ;   Yen Shin4 Author Orcid Image ;   HoJae Lee4 Author Orcid Image ;   Ruda Lee5 Author Orcid Image ;   Sang Min Lee2 Author Orcid Image ;   Je Young Hannah Sun2 Author Orcid Image ;   Ah Rah Lee2 Author Orcid Image ;   Si Yeun Yoon2 Author Orcid Image ;   Dong-ho Lee1 Author Orcid Image ;   Jihyung Moon1 Author Orcid Image ;   JinYeong Bak3 Author Orcid Image ;   Kyunghyun Cho6 Author Orcid Image ;   Jong-Woo Paik2 Author Orcid Image ;   Sungjoon Park1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Kyumin Park   1 * , MS ;   Myung Jae Baik   2 * , MD ;   YeongJun Hwang   3 * , MS ;   Yen Shin   4 , BS ;   HoJae Lee   4 , BS ;   Ruda Lee   5 , MA ;   Sang Min Lee   2 , PhD ;   Je Young Hannah Sun   2 , MD ;   Ah Rah Lee   2 , PhD ;   Si Yeun Yoon   2 , MA ;   Dong-ho Lee   1 , PhD ;   Jihyung Moon   1 , MS ;   JinYeong Bak   3 , PhD ;   Kyunghyun Cho   6 , PhD ;   Jong-Woo Paik   2 , PhD ;   Sungjoon Park   1 , PhD

1 SoftlyAI, Seoul, Republic of Korea

2 Department of Psychiatry, Kyung Hee University College of Medicine, Seoul, Republic of Korea

3 Department of Artificial Intelligence, Sungkyunkwan University, Suwon-si, Gyeonggi-do, Republic of Korea

4 KAIST, Daejeon, Republic of Korea

5 Department of Psychology, University of Pennsylvania, Philadelphia, PA, United States

6 Department of Computer Science, New York University, New York, NY, United States

*these authors contributed equally

Corresponding Author:

  • JinYeong Bak, PhD
  • Department of Artificial Intelligence
  • Sungkyunkwan University
  • Office 27306, Engineering Building 2, 2066 Seobu-ro Jangan-gu
  • Suwon-si, Gyeonggi-do 16419
  • Republic of Korea
  • Phone: +82 31 290 7104
  • Email: jy.bak@skku.edu