A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Boci Peng, Yun Zhu, Yongchao Liu, et al.
The first comprehensive survey of Graph Retrieval-Augmented Generation (GraphRAG), formalizing its workflow into graph-based indexing, graph-guided retrieval, and graph-enhanced generation.
Zulun Zhu, Tiancheng Huang, Kai Wang, et al.
A comprehensive survey of graph-based approaches that organize external knowledge to enhance retrieval-augmented generation in large language models.
Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, et al.
A systematic survey of Graph-based Retrieval-Augmented Generation (GraphRAG) for customizing large language models, covering techniques, applications, and future directions.
Unknown
LinearRAG proposes a linear graph-based retrieval-augmented generation method for efficient retrieval on large-scale corpora.
Unknown
This paper presents a unified framework for analyzing graph-based RAG methods, systematically comparing their components and performance to provide actionable insights for practitioners.
Unknown
This paper proposes a graph-based RAG framework that enhances document retrieval by integrating knowledge graphs with LLMs to improve answer accuracy and context relevance.
Unknown
GraphRAG enhances LLM-driven RAG for finance by using graph-based retrieval to reduce hallucinations and improve contextual coherence.
Unknown
This paper proposes an economical communication pipeline for LLM-based multi-agent systems, using a graph-based description of reasoning to reduce token costs while maintaining performance.
Unknown
GFM-RAG introduces a graph foundation model for retrieval augmented generation, enhancing knowledge integration through graph-based retrieval.
Caroline Pantofaru, Martial Hebert
This paper evaluates mean shift and graph-based segmentation algorithms using the Normalized Probabilistic Rand index for objective comparison.
Unknown
This paper proposes enhancing graph-based retrieval-augmented generation (RAG) with robust retrieval techniques to improve factual accuracy.
Junde Wu, Jiayuan Zhu, Yunli Qi
MedGraphRAG introduces a graph-based RAG framework to improve safety and accuracy of medical LLMs by structuring medical knowledge as a graph.