RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915385778896896 |
|---|---|
| author | Yang, Shuo Yu, Zijian Ying, Zhenzhe Dai, Yuqin Wang, Guoqing Lan, Jun Xu, Jinfeng Li, Jinze Ngai, Edith C. H. |
| author_facet | Yang, Shuo Yu, Zijian Ying, Zhenzhe Dai, Yuqin Wang, Guoqing Lan, Jun Xu, Jinfeng Li, Jinze Ngai, Edith C. H. |
| contents | The rapid proliferation of multimodal misinformation presents significant challenges for automated fact-checking systems, especially when claims are ambiguous or lack sufficient context. We introduce RAMA, a novel retrieval-augmented multi-agent framework designed for verifying multimedia misinformation. RAMA incorporates three core innovations: (1) strategic query formulation that transforms multimodal claims into precise web search queries; (2) cross-verification evidence aggregation from diverse, authoritative sources; and (3) a multi-agent ensemble architecture that leverages the complementary strengths of multiple multimodal large language models and prompt variants. Extensive experiments demonstrate that RAMA achieves superior performance on benchmark datasets, particularly excelling in resolving ambiguous or improbable claims by grounding verification in retrieved factual evidence. Our findings underscore the necessity of integrating web-based evidence and multi-agent reasoning for trustworthy multimedia verification, paving the way for more reliable and scalable fact-checking solutions. RAMA will be publicly available at https://github.com/kalendsyang/RAMA.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09174 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking Yang, Shuo Yu, Zijian Ying, Zhenzhe Dai, Yuqin Wang, Guoqing Lan, Jun Xu, Jinfeng Li, Jinze Ngai, Edith C. H. Computation and Language The rapid proliferation of multimodal misinformation presents significant challenges for automated fact-checking systems, especially when claims are ambiguous or lack sufficient context. We introduce RAMA, a novel retrieval-augmented multi-agent framework designed for verifying multimedia misinformation. RAMA incorporates three core innovations: (1) strategic query formulation that transforms multimodal claims into precise web search queries; (2) cross-verification evidence aggregation from diverse, authoritative sources; and (3) a multi-agent ensemble architecture that leverages the complementary strengths of multiple multimodal large language models and prompt variants. Extensive experiments demonstrate that RAMA achieves superior performance on benchmark datasets, particularly excelling in resolving ambiguous or improbable claims by grounding verification in retrieved factual evidence. Our findings underscore the necessity of integrating web-based evidence and multi-agent reasoning for trustworthy multimedia verification, paving the way for more reliable and scalable fact-checking solutions. RAMA will be publicly available at https://github.com/kalendsyang/RAMA.git. |
| title | RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.09174 |