Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
This work addresses the problem of efficient content moderation for online platforms, though it appears incremental as it builds on existing chain-of-thought and tool-augmentation methods.
The paper tackles the challenge of scalable content safety moderation by introducing Tool-MCoT, a small language model fine-tuned with tool-augmented chain-of-thought data, which achieves significant performance gains and balances accuracy with inference efficiency by selectively using tools.
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.