# Winning Solution For Meta KDD Cup' 24

arXiv: https://arxiv.org/abs/2410.00005 · HTML: https://mlsanity.com/paper/2410.00005/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2024.

## Built on by (most cited first, 2 of 2)

- [ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources](https://mlsanity.com/paper/2504.06271/) (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 describes the winning solutions of all tasks in Meta KDD Cup 24 from db3 team. The challenge is to build a RAG system from web sources and knowledge graphs. We are given multiple sources for each query to help us answer the question. The CRAG challenge involves three tasks: (1) condensing information from web pages into accurate answers, (2) integrating structured data from mock knowledge graphs, and (3) selecting and integrating critical data from extensive web pages and APIs to reflect real-world retrieval challenges. Our solution for Task #1 is a framework of web or open-data retrieval and answering. The large language model (LLM) is tuned for better RAG performance and less hallucination. Task #2 and Task #3 solutions are based on a regularized API set for domain questions and the API generation method using tuned LLM. Our knowledge graph API interface extracts directly relevant information to help LLMs answer correctly. Our solution achieves 1st place on all three tasks, achieving a score of 28.4%, 42.7%, and 47.8%, respectively.