# Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering

Source: [Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering](<https://www.sota2.com/research/paper/68fa7a421e209131cea81fb6>)

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

Data updated: 2025-10-28T13:57:19.622Z

Authors: Zijian Zhang, Xiaocheng Zhang, Yang Zhou, Zhimin Lin, Peng Yan

Published: 2025-07-29T06:07:59.000Z

## Abstract

Vision Large Language Models (VLLMs) have improved multi-modal understanding and visual question answering (VQA), but still suffer from hallucinated answers. Multi-modal Retrieval-Augmented Generation (RAG) helps address these issues by incorporating external information, yet challenges remain in visual context comprehension, multi-source retrieval, and multi-turn interactions. To address these challenges, Meta constructed the CRAG-MM benchmark and launched the CRAG-MM Challenge at KDD Cup 2025, which consists of three tasks. This paper describes the solutions of all tasks in Meta KDD Cup'25 from BlackPearl team. We use a single model for each task, with key methods including data augmentation, RAG, reranking, and multi-task fine-tuning. Our solution achieve automatic evaluation rankings of 3rd, 3rd, and 1st on the three tasks, and win second place in Task3 after human evaluation.

## 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/2507.21520>)

[PDF](<https://arxiv.org/pdf/2507.21520.pdf>)