Revisiting the Solution of Meta KDD Cup 2024: CRAG

Jie Ouyang, Yucong Luo, Mingyue Cheng, Daoyu Wang, Shuo Yu, Qi Liu, Enhong Chen

Keywords: Retrieval-Augmented Generation, Large Language Model

TL;DR: This paper presents team APEX's solution for the Meta KDD CUP 2024 CRAG Challenge, proposing a routing-based domain and dynamic adaptive RAG pipeline that achieved second place in Tasks 2&3, with the implementation available on GitHub.

Abstract: This paper presents the solution of our team APEX in the Meta KDD CUP 2024: CRAG Comprehensive RAG Benchmark Challenge. The CRAG benchmark addresses the limitations of existing QA benchmarks in evaluating the diverse and dynamic challenges faced by Retrieval-Augmented Generation (RAG) systems. It provides a more comprehensive assessment of RAG performance and contributes to advancing research in this field. We propose a routing-based domain and dynamic adaptive RAG pipeline, which performs specific processing for the diverse and dynamic nature of the question in all three stages: retrieval, augmentation, and generation. Our method achieved superior performance on CRAG and ranked 2nd for Task 2\&3 on the final competition leaderboard. Our implementation is available at this link: https://github.com/USTCAGI/CRAG-in-KDD-Cup2024.

Submission Number: 3