| Creators: |
Riekers, Nils and Risius, Marten and Cheng, Tong |
| Title: |
MAXplain: A Multi-Agent System for Interactive Multimodal Hate Speech Detection |
| Item Type: |
Conference or Workshop Item |
| Event Title: |
(Proceedings of the) 33rd ACM International Conference on Multimedia (MM) |
| Event Location: |
Dublin, Ireland |
| Event Dates: |
October, 27-31, 2025 |
| Projects: |
IDI |
| Page Range: |
pp. 13516-13518 |
| Additional Information: |
Open Access |
| Date: |
October 2025 |
| Divisions: |
Informationsmanagement |
| Abstract (ENG): |
Multimodal hate speech detection targets offensive content expressed through combinations of modalities such as text and images, which often evade detection when analyzed separately. We introduce MAXplain, an interactive framework that addresses both issues via a configurable LLM-based multi-agent architecture. Specialized agents handle distinct subtasks and exchange information through structured dialogues, enabling intrinsic explainability and improved accuracy. The web interface supports human-in-the-loop interaction, including real-time adjustment of agent behaviors and evaluation rules. A browser plugin enables direct inspection of online content. While demonstrated for hate speech detection, MAXplain also supports rapid prototyping for other multimodal tasks. |
| Forthcoming: |
No |
| Language: |
English |
| Uncontrolled Keywords: |
Multi-agent systems, Explainable AI, Large language models, Multimodal analysis, Hateful meme detection, Human-in-the-loop |
| Link eMedia: |
Download |
| Citation: |
Riekers, Nils and Risius, Marten and Cheng, Tong
(2025)
MAXplain: A Multi-Agent System for Interactive Multimodal Hate Speech Detection.
In: (Proceedings of the) 33rd ACM International Conference on Multimedia (MM), October, 27-31, 2025, Dublin, Ireland, pp. 13516-13518.
|
