Large Language Models for Automatic Detection of Sensitive Topics
This addresses the need for automated content moderation to assist human moderators in online communities, though it is incremental as it applies existing LLMs to a specific domain.
The study tackled the problem of detecting sensitive topics in online content by evaluating five large language models (LLMs) on mental well-being datasets, finding that GPT-4o achieved 99.5% accuracy and a 0.99 F1-score, indicating high potential for integration into moderation workflows.
Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus solely on flagged content that may pose potential risks. Rapidly advancing large language models (LLMs) are known for their capability to understand and process natural language and so present a potential solution to support this process. This study explores the capabilities of five LLMs for detecting sensitive messages in the mental well-being domain within two online datasets and assesses their performance in terms of accuracy, precision, recall, F1 scores, and consistency. Our findings indicate that LLMs have the potential to be integrated into the moderation workflow as a convenient and precise detection tool. The best-performing model, GPT-4o, achieved an average accuracy of 99.5\% and an F1-score of 0.99. We discuss the advantages and potential challenges of using LLMs in the moderation workflow and suggest that future research should address the ethical considerations of utilising this technology.