Harmful Suicide Content Detection

TL;DR

This paper introduces a new multi-modal benchmark and detection task for classifying harmful online suicide content into five levels, utilizing large language models and expert annotations to improve moderation and safety.

Contribution

It proposes a novel harmful suicide content detection task, develops a Korean multi-modal benchmark with expert labels, and explores LLM-based strategies for content moderation.

Findings

Developed a multi-modal Korean benchmark with expert annotations.

Explored LLM strategies for detecting harmful content.

Publicized the benchmark with ethical verification.

Abstract

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.