检索增强生成(RAG)是一种框架,使大型语言模型(LLMs)能够通过整合外部知识库来提高准确性并减少幻觉。在本文中,我们介绍了一个混合RAG系统,该系统通过一套全面的优化措施得到增强,显著提升了检索质量、增强了推理能力,并改进了数值计算能力。我们精化了网页中的文本块和表格,添加了属性预测器以减少幻觉,实施了LLM知识提取器和知识图谱提取器,并最终构建了一种包含所有参考文献的推理策略。我们在CRAG数据集上通过Meta CRAG KDD Cup 2024竞赛对我们的系统进行了评估。本地评估和在线评估均表明,我们的系统显著增强了复杂推理能力。在本地评估中,与基线模型相比,我们显著提高了准确性并降低了错误率,取得了分数的显著提升。同时,我们在在线评估中也取得了出色的结果,展示了所提出系统的性能和泛化能力。我们系统的源代码发布在\url{https://gitlab.aicrowd.com/shizueyy/crag-new}。
英文摘要:
Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced through a comprehensive suite of optimizations that significantly improve retrieval quality, augment reasoning capabilities, and refine numerical computation ability. We refined the text chunks and tables in web pages, added attribute predictors to reduce hallucinations, conducted LLM Knowledge Extractor and Knowledge Graph Extractor, and finally built a reasoning strategy with all the references. We evaluated our system on the CRAG dataset through the Meta CRAG KDD Cup 2024 Competition. Both the local and online evaluations demonstrate that our system significantly enhances complex reasoning capabilities. In local evaluations, we have significantly improved accuracy and reduced error rates compared to the baseline model, achieving a notable increase in scores. In the meanwhile, we have attained outstanding results in online assessments, demonstrating the performance and generalization capabilities of the proposed system. The source code for our system is released in \url{https://gitlab.aicrowd.com/shizueyy/crag-new}.
RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration
PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization
Gaoling School of Artificial Intelligence\ University of China Beijing China;School of Information Technology;Gaoling School of Artificial Intelligence\ University of China
R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Meituan(美团)
CARE-RAG - Clinical Assessment and Reasoning in RAG
Department of Computer Science(计算机科学系);University of Texas at Austin(德克萨斯大学奥斯汀分校);Behavioral Science and Psychiatry(行为科学与精神病学);Department of Statistics(统计学系);University of Michigan(密歇根大学);School of Information(信息学院)
Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology(计算技术研究所);Chinese Academy of Sciences(中国科学院);University of Chinese Academy of Sciences(中国科学院大学)
KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
School of Biomedical Engineering, Tsinghua, China(清华大学生物医学工程学院);School of Informatics, Xiamen University, China(厦门大学信息学院);Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学计算机科学与技术系);Dept. of Computer Science and Technology, Northeastern University, Shenyang, China(东北大学沈阳校区计算机科学与技术系);Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所)
IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval
East China Normal University(华东师范大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Shanghai for Science and Technology(上海科技大学);Harbin Engineering University(哈尔滨工程大学)
Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(北京未来区块链与隐私计算先进创新中心);School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Meituan(美团)
EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes
Tsinghua University(清华大学);Zhejiang University(浙江大学);Ant Group(蚂蚁集团);Massachusetts Institute of Technology(麻省理工学院);UC Berkeley(加州大学伯克利分校);The University of Hong Kong(香港大学);National University of Singapore(新加坡国立大学)
LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law
Ahsanullah University of Science and Technology(阿赫萨努拉科技大学);Jashore University of Science and Technology(杰肖尔科技大学);American International University - Bangladesh(美国国际大学-孟加拉)
Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
Zhejiang University(浙江大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);South China University of Technology(华南理工大学);University of British Columbia(不列颠哥伦比亚大学);Fudan University(复旦大学);University of Hong Kong(香港大学)
PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning
School of Future Technology, South China University of Technology(华南理工大学未来技术学院);TikTok Inc(字节跳动公司);School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);School of Software Engineering, Sun Yat-sen University(中山大学软件工程学院)