DB3 Team's Solution For Meta KDD Cup' 25
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_ | 1866908758177742848 |
|---|---|
| author | Xia, Yikuan Chen, Jiazun Zhan, Yirui Zhao, Suifeng Jiang, Weipeng Zhang, Chaorui Han, Wei Bai, Bo Gao, Jun |
| author_facet | Xia, Yikuan Chen, Jiazun Zhan, Yirui Zhao, Suifeng Jiang, Weipeng Zhang, Chaorui Han, Wei Bai, Bo Gao, Jun |
| contents | This paper presents the db3 team's winning solution for the Meta CRAG-MM Challenge 2025 at KDD Cup'25. Addressing the challenge's unique multi-modal, multi-turn question answering benchmark (CRAG-MM), we developed a comprehensive framework that integrates tailored retrieval pipelines for different tasks with a unified LLM-tuning approach for hallucination control. Our solution features (1) domain-specific retrieval pipelines handling image-indexed knowledge graphs, web sources, and multi-turn conversations; and (2) advanced refusal training using SFT, DPO, and RL. The system achieved 2nd place in Task 1, 2nd place in Task 2, and 1st place in Task 3, securing the grand prize for excellence in ego-centric queries through superior handling of first-person perspective challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09681 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DB3 Team's Solution For Meta KDD Cup' 25 Xia, Yikuan Chen, Jiazun Zhan, Yirui Zhao, Suifeng Jiang, Weipeng Zhang, Chaorui Han, Wei Bai, Bo Gao, Jun Information Retrieval Artificial Intelligence Computation and Language Machine Learning This paper presents the db3 team's winning solution for the Meta CRAG-MM Challenge 2025 at KDD Cup'25. Addressing the challenge's unique multi-modal, multi-turn question answering benchmark (CRAG-MM), we developed a comprehensive framework that integrates tailored retrieval pipelines for different tasks with a unified LLM-tuning approach for hallucination control. Our solution features (1) domain-specific retrieval pipelines handling image-indexed knowledge graphs, web sources, and multi-turn conversations; and (2) advanced refusal training using SFT, DPO, and RL. The system achieved 2nd place in Task 1, 2nd place in Task 2, and 1st place in Task 3, securing the grand prize for excellence in ego-centric queries through superior handling of first-person perspective challenges. |
| title | DB3 Team's Solution For Meta KDD Cup' 25 |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.09681 |