Tool-MCoT：用于内容安全审核的工具增强多模态链式思维
Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
AI总结：
本文提出Tool-MCoT，一种基于工具增强的多模态链式思维模型，用于提升内容安全审核的效率与准确性，通过训练小语言模型以有效利用外部工具进行推理和决策。
摘要：
在线平台和用户内容的快速增长要求强大的内容审核系统，能够处理各种媒体类型的复杂输入。尽管大语言模型（LLMs）有效，但其高计算成本和延迟对可扩展部署构成重大挑战。为了解决这一问题，我们引入Tool-MCoT，一种经过外部框架增强的小语言模型（SLM），用于内容安全审核。通过在LLM生成的工具增强链式思维数据上训练我们的模型，我们证明SLM能够有效利用这些工具来提升其推理和决策能力。我们的实验表明，经过微调的SLM在性能上取得了显著提升。此外，我们还展示了模型能够选择性地使用这些工具，在必要时调用工具，从而在审核准确性和推理效率之间取得平衡。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
