Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning

arXiv:2310.03400v2 Announce Type: replace
Abstract: Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach is to use a discriminative model to classify the content, but this method often requires strict data engineering, otherwise it will face unacceptable overfitting. With the successful development of Large Language Models (LLMs) in recent years, LLM-based methods have become a …

abstract arxiv communication content moderation cs.lg daily data data engineering engineering express fine-tuning internet language language models large language large language models making moderation opinions people supervised fine-tuning type