Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation

TL;DR

Tool-MCoT introduces a fine-tuned small language model that leverages external tools and chain-of-thought reasoning to enhance content safety moderation while reducing computational costs.

Contribution

It presents a novel approach to train small language models with tool-augmented data for improved moderation efficiency and accuracy.

Findings

Significant performance gains over baseline models.

Effective learning to use tools selectively for efficiency.

Balanced moderation accuracy and inference speed.

Abstract

The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. While large language models (LLMs) are effective, their high computational cost and latency present significant challenges for scalable deployment. To address this, we introduce Tool-MCoT, a small language model (SLM) fine-tuned for content safety moderation leveraging external framework. By training our model on tool-augmented chain-of-thought data generated by LLM, we demonstrate that the SLM can learn to effectively utilize these tools to improve its reasoning and decision-making. Our experiments show that the fine-tuned SLM achieves significant performance gains. Furthermore, we show that the model can learn to use these tools selectively, achieving a balance between moderation accuracy and inference efficiency by calling tools only when necessary.