# DB3 Team's Solution For Meta KDD Cup' 25

Source: [DB3 Team's Solution For Meta KDD Cup' 25](<https://www.sota2.com/research/paper/68fa7b401e209131cea874f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-14T05:00:12.520Z

Authors: Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao

Published: 2025-08-12T08:27:53.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.09681>)

[PDF](<https://arxiv.org/pdf/2509.09681.pdf>)
