DB3 Team's Solution For Meta KDD Cup' 25
This addresses the problem of multi-modal, multi-turn question answering with ego-centric queries for competition participants, representing an incremental improvement through integration of existing techniques.
The paper presents a winning solution for the Meta CRAG-MM Challenge 2025, tackling multi-modal, multi-turn question answering by integrating tailored retrieval pipelines with LLM-tuning for hallucination control, achieving top placements (2nd in Task 1, 2nd in Task 2, and 1st in Task 3) and securing the grand prize.
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.