HighlightLecture notes in computer science

EcoRAG: A Multi-hop Economic QA Benchmark for Retrieval Augmented Generation Using Knowledge Graphs

A multi-hop economic question answering benchmark for retrieval augmented generation using knowledge graphs.

EcoRAG is a benchmark designed to evaluate the performance of retrieval augmented generation models on multi-hop economic question answering tasks. It uses knowledge graphs and aims to improve the accuracy and efficiency of these models. The benchmark provides a comprehensive evaluation framework for researchers and developers working in this area.

Based on: EcoRAG: A Multi-hop Economic QA Benchmark for Retrieval Augmented Generation Using Knowledge Graphs · Lecture notes in computer science

HighlightIEEE Wireless Communications

When Knowledge Graph Meets Retrieval Augmented Generation for Wireless Networks: A Tutorial and Case Study

A tutorial and case study on integrating knowledge graphs into the Retrieval-Augmented Generation architecture.

This paper proposes a GraphRAG framework that combines knowledge graphs with RAG to enhance networking applications. It reviews existing RAG applications in networking, identifies their limitations, and presents a domain-adapted GraphRAG framework for wireless network optimization. A case study demonstrates the effectiveness of GraphRAG in channel gain prediction.

Based on: When Knowledge Graph Meets Retrieval Augmented Generation for Wireless Networks: A Tutorial and Case Study · IEEE Wireless Communications

HighlightarXiv (Cornell University)

A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

Survey on Graph-based Retrieval-Augmented Generation (GraphRAG) for customizing large language models.

This survey presents a systematic analysis of GraphRAG, a paradigm that addresses traditional RAG limitations through graph-structured knowledge representation and efficient retrieval techniques. It examines current implementations across various professional domains and identifies key technical challenges and research directions. The survey aims to revolutionize domain-specific LLM applications by seamlessly integrating external knowledge bases.

Based on: A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models · arXiv (Cornell University)

Highlightopenalex.org

GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs

A framework that uses graph neural networks to enhance retrieval in knowledge graph question answering.

The GNN-RAG framework utilizes lightweight graph neural networks for efficient graph retrieval. It learns to assign importance weights to nodes and their neighboring nodes, enabling effective handling of context from distant nodes. Experimental results show improved retrieval performance on two widely used KGQA benchmarks, outperforming or matching GPT-4 performance.

Based on: GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs

HighlightAcademic Journal of Science and Technology

Knowledge Graph Combined with Retrieval-Augmented Generation for Enhancing LMs Reasoning: A Survey

A survey on integrating knowledge graphs with retrieval-augmented generation to enhance large language models' reasoning abilities.

The paper surveys research on combining knowledge graphs with retrieval-augmented generation (RAG) to improve large language models' (LLMs') reasoning. It reviews current technical approaches and discusses challenges and future trends in this field. The integrated approach aims to enhance LLMs' knowledge representation and reasoning abilities.

Based on: Knowledge Graph Combined with Retrieval-Augmented Generation for Enhancing LMs Reasoning: A Survey · Academic Journal of Science and Technology

HighlightElectronics

Document GraphRAG: Knowledge Graph Enhanced Retrieval Augmented Generation for Document Question Answering Within the Manufacturing Domain

A novel framework that incorporates knowledge graphs into the RAG pipeline for document question answering.

This study introduces Document Graph RAG (GraphRAG), a framework that enhances retrieval robustness and answer generation by incorporating knowledge graphs. The evaluation demonstrates consistent performance gains over a naive RAG baseline across both retrieval and generation metrics. GraphRAG improves context relevance metrics, particularly for multi-hop questions.

Based on: Document GraphRAG: Knowledge Graph Enhanced Retrieval Augmented Generation for Document Question Answering Within the Manufacturing Domain · Electronics

HighlightCommunications in computer and information science

Knowledge Graph-Based Legal Query System with LLM and Retrieval Augmented Generation

A paper proposing a knowledge graph-based legal query system using large language models and retrieval augmented generation.

The authors propose a knowledge graph-based legal query system that leverages large language models and retrieval augmented generation to improve query efficiency. The system is designed for legal applications, utilizing a knowledge graph to store and retrieve relevant information. This approach aims to enhance the accuracy and speed of legal queries by combining the strengths of both knowledge graphs and large language models.

Based on: Knowledge Graph-Based Legal Query System with LLM and Retrieval Augmented Generation · Communications in computer and information science

Highlightopenalex.org

GRAG: Graph Retrieval-Augmented Generation

A method for graph retrieval-augmented generation that tackles networked documents.

GRAG addresses limitations of naive RAG by retrieving textual subgraphs and integrating joint textual and topological information into LLMs. It proposes a divide-and-conquer strategy for efficient retrieval and incorporates textual graphs into LLMs through two views. Experiments demonstrate GRAG's effectiveness in multi-hop reasoning on textual graphs.

Based on: GRAG: Graph Retrieval-Augmented Generation

HighlightJournal of Engineering Design

Multilingual graph retrieval-augmented generation for product design using design knowledge

A framework that integrates multilingual design knowledge to improve product design using large language models.

The authors propose a framework, MDKG-RAG, which extracts and integrates multilingual design knowledge from various sources. This framework uses large language models to dynamically optimize and extract relevant information for product design. Experiments demonstrate the effectiveness of MDKG-RAG in improving answer similarity and context recall.

Based on: Multilingual graph retrieval-augmented generation for product design using design knowledge · Journal of Engineering Design

HighlightScientific Reports

Construction of intelligent decision support systems through integration of retrieval-augmented generation and knowledge graphs

Proposes a framework for intelligent decision support systems using retrieval-augmented generation and knowledge graphs.

The article presents a novel architecture that combines generative models with structured knowledge representations to improve decision accuracy, transparency, and context relevance. The proposed method is tested on three areas: financial services, healthcare management, and supply chain management. It shows improvement in cross-domain reasoning and ambiguous queries compared to using either technology alone.

Based on: Construction of intelligent decision support systems through integration of retrieval-augmented generation and knowledge graphs · Scientific Reports

HighlightFrontiers in Artificial Intelligence

Advancing engineering research through context-aware and knowledge graph–based retrieval-augmented generation

A study on improving the accuracy of large language models in generating technical content.

The authors propose a new Retrieval-Augmented Generation (RAG) model for engineering domains, which uses contextual information to improve relevance. The model is built on the n8n automation system and can retrieve densely linked concepts from multiple knowledge graphs. This approach aims to mitigate the shortcomings of traditional RAG techniques in treating isolated information.

Based on: Advancing engineering research through context-aware and knowledge graph–based retrieval-augmented generation · Frontiers in Artificial Intelligence

HighlightJournal of the American Medical Informatics Association

Detecting emergencies in patient portal messages using large language models and knowledge graph-based retrieval-augmented generation

Study on using large language models and a knowledge graph to triage patient messages for emergency care.

The study evaluates the effectiveness of four models in detecting emergency messages in patient portals, with a focus on integrating large language models (LLMs) with a knowledge graph. The results show that the model incorporating a global search within the knowledge graph outperformed other approaches. This research contributes to the development of AI-assisted triage systems for improving patient safety.

Based on: Detecting emergencies in patient portal messages using large language models and knowledge graph-based retrieval-augmented generation · Journal of the American Medical Informatics Association