Harmful suicide content on the Internet is a significant risk factor inducing suicidal thoughts and behaviors among vulnerable populations. Despite global efforts, existing resources are insufficient, specifically in high-risk regions like the Republic of Korea. Current research mainly focuses on understanding negative effects of such content or suicide risk in individuals, rather than on automatically detecting the harmfulness of content. To fill this gap, we introduce a harmful suicide content detection task for classifying online suicide content into five harmfulness levels. We develop a multi-modal benchmark and a task description document in collaboration with medical professionals, and leverage large language models (LLMs) to explore efficient methods for moderating such content. Our contributions include proposing a novel detection task, a multi-modal Korean benchmark with expert annotations, and suggesting strategies using LLMs to detect illegal and harmful content. Owing to the potential harm involved, we publicize our implementations and benchmark, incorporating an ethical verification process.
@article{arxiv.2407.13942,
title = {Harmful Suicide Content Detection},
author = {Kyumin Park and Myung Jae Baik and YeongJun Hwang and Yen Shin and HoJae Lee and Ruda Lee and Sang Min Lee and Je Young Hannah Sun and Ah Rah Lee and Si Yeun Yoon and Dong-ho Lee and Jihyung Moon and JinYeong Bak and Kyunghyun Cho and Jong-Woo Paik and Sungjoon Park},
journal= {arXiv preprint arXiv:2407.13942},
year = {2024}
}