# Revisiting the Solution of Meta KDD Cup 2024: CRAG

arXiv: https://arxiv.org/abs/2409.15337 · HTML: https://mlsanity.com/paper/2409.15337/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Unlocking the Potential of Large Language Models for Explainable Recommendations](https://mlsanity.com/paper/2312.15661/) (2023)
- [Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform](https://mlsanity.com/paper/2403.08305/) (2024)
- [Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling](https://mlsanity.com/paper/2309.10435/) (2023)

## Built on by (most cited first, 5 of 5)

- [HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04800/) (2025)
- [AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval](https://mlsanity.com/paper/2510.10397/) (2025)
- [Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2410.21779/) (2024)
- [KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering](https://mlsanity.com/paper/2509.04716/) (2025)
- [CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering](https://mlsanity.com/paper/2604.26176/) (2026)

## Abstract (arXiv)

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.