Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.06205 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914455063887872 |
|---|---|
| author | Zhang, Shutong Zhou, Dylan Liu, Yinxiao Yang, Yang Luo, Huiwen Zou, Wenfei |
| author_facet | Zhang, Shutong Zhou, Dylan Liu, Yinxiao Yang, Yang Luo, Huiwen Zou, Wenfei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06205 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation Zhang, Shutong Zhou, Dylan Liu, Yinxiao Yang, Yang Luo, Huiwen Zou, Wenfei Computation and Language Artificial Intelligence 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. |
| title | Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06205 |