针对复杂问答设计动态自适应检索增强生成框架，提升系统应对多样问题的能力。
Revisiting the Solution of Meta KDD Cup 2024: CRAG
- 基于路由机制按领域动态选择处理策略
- 在CRAG基准上任务2&3均获第二名
- 适合需要精准响应多变问题的场景
本文介绍我们团队APEX在Meta KDD Cup 2024：CRAG综合RAG基准挑战赛中的解决方案。CRAG基准旨在解决现有问答评估基准在衡量检索增强生成（RAG）系统所面临多样化与动态性挑战方面的不足，提供了更全面的RAG性能评估方式，推动该领域研究发展。我们提出一种基于路由的领域与动态自适应RAG流程，在检索、增强和生成三个阶段针对问题的多样性和动态性进行针对性处理。该方法在CRAG基准上表现优异，在最终竞赛排行榜中任务2与任务3均位列第二。代码实现已公开于：https://github.com/USTCAGI/CRAG-in-KDD-Cup2024。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。