Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.02530 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915661692796928 |
|---|---|
| author | He, Yuxiang Zhao, Jian Yuan, Yuchen Zhang, Tianle Cai, Wei Cheng, Haojie Shi, Ziyan Zhu, Ming Tang, Haichuan Zhang, Chi Li, Xuelong |
| author_facet | He, Yuxiang Zhao, Jian Yuan, Yuchen Zhang, Tianle Cai, Wei Cheng, Haojie Shi, Ziyan Zhu, Ming Tang, Haichuan Zhang, Chi Li, Xuelong |
| contents | The exponential growth of digital content presents significant challenges for content safety. Current moderation systems, often based on single models or fixed pipelines, exhibit limitations in identifying implicit risks and providing interpretable judgment processes. To address these issues, we propose Aetheria, a multimodal interpretable content safety framework based on multi-agent debate and collaboration.Employing a collaborative architecture of five core agents, Aetheria conducts in-depth analysis and adjudication of multimodal content through a dynamic, mutually persuasive debate mechanism, which is grounded by RAG-based knowledge retrieval.Comprehensive experiments on our proposed benchmark (AIR-Bench) validate that Aetheria not only generates detailed and traceable audit reports but also demonstrates significant advantages over baselines in overall content safety accuracy, especially in the identification of implicit risks. This framework establishes a transparent and interpretable paradigm, significantly advancing the field of trustworthy AI content moderation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration He, Yuxiang Zhao, Jian Yuan, Yuchen Zhang, Tianle Cai, Wei Cheng, Haojie Shi, Ziyan Zhu, Ming Tang, Haichuan Zhang, Chi Li, Xuelong Artificial Intelligence The exponential growth of digital content presents significant challenges for content safety. Current moderation systems, often based on single models or fixed pipelines, exhibit limitations in identifying implicit risks and providing interpretable judgment processes. To address these issues, we propose Aetheria, a multimodal interpretable content safety framework based on multi-agent debate and collaboration.Employing a collaborative architecture of five core agents, Aetheria conducts in-depth analysis and adjudication of multimodal content through a dynamic, mutually persuasive debate mechanism, which is grounded by RAG-based knowledge retrieval.Comprehensive experiments on our proposed benchmark (AIR-Bench) validate that Aetheria not only generates detailed and traceable audit reports but also demonstrates significant advantages over baselines in overall content safety accuracy, especially in the identification of implicit risks. This framework establishes a transparent and interpretable paradigm, significantly advancing the field of trustworthy AI content moderation. |
| title | Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.02530 |