HighlightCurated by Aramai Editorial

Leveraging LLM based Retrieval-Augmented Generation for Legal Knowledge Graph Completion

A paper proposing a model for legal knowledge graph completion using Large Language Models and retrieval-augmented generation.

The authors propose RA-KG-LLM, a model that combines the generative capabilities of Large Language Models with retrieval-augmented technology to enhance semantic information and interrelations mining in knowledge graphs. The model is evaluated on five real datasets, including Cail2022, where it achieves better performance than state-of-the-art related works. This paper aims to improve the completeness and accuracy of legal knowledge graphs.

Based on: Leveraging LLM based Retrieval-Augmented Generation for Legal Knowledge Graph Completion

HighlightCurated by Aramai Editorial

Graph Retrieval-Augmented Generation: A Survey

A survey on GraphRAG methodologies for retrieval-augmented generation.

The paper provides a comprehensive overview of GraphRAG, a framework that leverages structural information in databases to improve the accuracy and context-awareness of large language models. It formalizes the GraphRAG workflow and outlines core technologies and training methods. The survey also examines downstream tasks, application domains, evaluation methodologies, and industrial use cases.

Based on: Graph Retrieval-Augmented Generation: A Survey · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation

A paper proposing TRACE, a method for constructing knowledge-grounded reasoning chains to enhance multi-hop question answering.

The authors propose TRACE, a method that constructs knowledge-grounded reasoning chains to improve multi-hop question answering. TRACE uses a KG Generator and Autoregressive Reasoning Chain Constructor to build reasoning chains from retrieved documents. Experimental results show an average performance improvement of up to 14.03% compared to using all retrieved documents.

Based on: TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation

HighlightCurated by Aramai Editorial

Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation

A study on the limitations and failures of knowledge graph-based retrieval-augmented generation systems.

The paper identifies eight key areas of concern in existing KG-based RAG methods, including misinterpretation of question context and incorrect relation mapping. It proposes a new approach, Mindful-RAG, which re-engineers the retrieval process to be more intent-driven and contextually aware. The authors aim to improve the reliability and effectiveness of KG-RAG systems through enhanced reasoning capabilities and structural limitations of knowledge graphs.

Based on: Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation

HighlightCurated by Aramai Editorial

Retrieval-Augmented Generation with Graphs (GraphRAG)

A survey on retrieval-augmented generation with graphs, a technique for enhancing downstream tasks by retrieving information from external sources.

The paper presents a comprehensive survey of GraphRAG, a framework that combines graph-structured data with retrieval-augmented generation. It defines key components and reviews techniques tailored to different domains. The authors also discuss research challenges and potential directions for future work.

Based on: Retrieval-Augmented Generation with Graphs (GraphRAG) · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

Enhancing Retrieval Augmented Generation Systems with Knowledge Graphs

A paper proposing a comprehensive approach to enriching knowledge graphs.

The authors introduce a methodology that integrates key phrase extraction, node embedding generation, and an autonomous updating agent to create a connected knowledge graph. They also explore the incorporation of traditional vector search to enhance contextual understanding. The results show a substantial improvement in accuracy compared to traditional KG approaches.

Based on: Enhancing Retrieval Augmented Generation Systems with Knowledge Graphs

HighlightCurated by Aramai Editorial

TKG-RAG: A Retrieval-Augmented Generation Framework with Text-chunk Knowledge Graph

A retrieval-augmented generation framework that utilizes a text-chunk knowledge graph to improve performance.

The authors propose TKG-RAG, a framework that constructs a text-chunk knowledge graph automatically from domain text. This framework improves Retrieval-Augmented Generation (RAG) performance by addressing limitations such as noise and redundant information in retrieved text chunks. Comparative experiments show that TKG-RAG achieves better accuracy and F1 scores while reducing token consumption.

Based on: TKG-RAG: A Retrieval-Augmented Generation Framework with Text-chunk Knowledge Graph

HighlightCurated by Aramai Editorial

A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence

Survey on neurosymbolic AI's potential to ease testing and evaluation processes.

The paper surveys the current state of neurosymbolic artificial intelligence (AI), which combines symbolic and sub-symbolic AI. It explores how neurosymbolic applications can simplify verification, validation, testing, and evaluation processes. The authors analyze taxonomies, algorithms, and techniques used in current neurosymbolic applications.

Based on: A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence · IEEE Transactions on Artificial Intelligence

HighlightCurated by Aramai Editorial

Personalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach

A study proposing a patient-centric digital twin framework for diabetes care using personal health knowledge graphs.

The authors develop a real-time, patient-centric digital twin framework built on personal health knowledge graphs (PHKGs) to revolutionize diabetes management. This framework integrates data from diverse sources and enables seamless information access while ensuring high accuracy in data representation and health insights. The study demonstrates the versatility of their approach by applying it to different use cases in diabetes management.

Based on: Personalized Diabetes Management with Digital Twins: A Patient-Centric Knowledge Graph Approach · Journal of Personalized Medicine

HighlightCurated by Aramai Editorial

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

A method for question answering on textual graphs using retrieval-augmented generation.

The authors propose G-Retriever, a framework for question-answering on textual graphs. They introduce a new approach called retrieval-augmented generation (RAG) and formulate the task as a Prize-Collecting Steiner Tree optimization problem to mitigate hallucination. The method is evaluated on various textual graph tasks and outperforms baselines.

Based on: G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

TCM MLKG-RAG: Traditional Chinese Medicine Intelligent Diagnosis Based on Multi-Layer Knowledge Graph Retrieval-Augmented Generation

A retrieval-augmented generation model for traditional Chinese medicine knowledge graph.

The authors propose a TCM knowledge graph RAG that integrates multi-layered knowledge bases to address the issue of redundant data volumes in TCM search engines. The model uses two retrieval methods: keyword retrieval and therapy retrieval, which are designed to search for information on TCM-specific terms and locate diseases based on medical and patient information.

Based on: TCM MLKG-RAG: Traditional Chinese Medicine Intelligent Diagnosis Based on Multi-Layer Knowledge Graph Retrieval-Augmented Generation

HighlightCurated by Aramai Editorial

Enhancing Knowledge Graph Completion with Retrieval-Augmented Generation Using Large Language Models

A study introducing a framework for Knowledge Graph Completion using Large Language Models and Retrieval-Augmented Generation.

The authors propose an innovative framework for Knowledge Graph Completion leveraging Large Language Models. The framework treats KG triples as textual prompts to retrieve relevant information from knowledge bases, generating contextually accurate responses. A retrieval reranking strategy refines predictions by incorporating outputs from a pre-trained KGC model.

Based on: Enhancing Knowledge Graph Completion with Retrieval-Augmented Generation Using Large Language Models