HighlightCurated by Aramai Editorial

Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching

A proposed model for schema matching using knowledge graphs and retrieval-augmented generation.

The authors propose a Knowledge Graph-based Retrieval-Augmented Generation model (KG-RAG4SM) to address semantic ambiguities in schema matching. The model introduces novel vector-based, graph traversal-based, and query-based graph retrievals. Experimental results show that KG-RAG4SM outperforms state-of-the-art methods in terms of precision and F1 score on various datasets.

Based on: Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

A Retrieval-Augmented Generation Framework Based on a Knowledge Graph of Cybersecurity Vulnerabilities in Power Networks

Proposes a retrieval-augmented generation framework for power grid cybersecurity.

This paper presents a framework that integrates knowledge graphs with large language models to enhance their accuracy and practicality in decision support. The framework consists of seven key steps, including knowledge modeling, extraction, storage, and problem-solving. Experimental evaluation demonstrates the effectiveness of the proposed framework, achieving high scores across six metrics.

Based on: A Retrieval-Augmented Generation Framework Based on a Knowledge Graph of Cybersecurity Vulnerabilities in Power Networks · IEEE Access

HighlightCurated by Aramai Editorial

Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs

A paper proposing a multi-objective multi-armed bandit enhanced RAG framework for knowledge graphs.

The authors introduce a framework that adapts to non-stationary environments by selecting the most suitable retrieval method based on user feedback and historical performance. This approach is applied to Retrieval-Augmented Generation (RAG) on knowledge graphs, aiming to enhance reasoning capabilities of large language models. Experiments demonstrate improved performance in both stationary and non-stationary settings.

Based on: Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs · Proceedings of the AAAI Conference on Artificial Intelligence

HighlightCurated by Aramai Editorial

SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation

A paper proposing a novel method called SimGRAG for knowledge graph-driven retrieval-augmented generation.

The authors propose SimGRAG, a two-stage process that aligns query texts and KG structures using an LLM to transform queries into a desired graph pattern. They also develop an optimized retrieval algorithm. Experiments show that SimGRAG outperforms state-of-the-art methods in question answering and fact verification.

Based on: SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation

HighlightCurated by Aramai Editorial

Safeguarding large language models: a survey

A systematic literature review on safety mechanisms for Large Language Models.

The paper discusses the challenges and potential enhancements of safety mechanisms for LLMs, aiming to ensure ethical use within prescribed boundaries. It provides an overview of current research in this area. The authors identify major challenges and propose ways to improve these mechanisms.

Based on: Safeguarding large language models: a survey

HighlightCurated by Aramai Editorial

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

Paper proposing a method to integrate multilingual knowledge graphs into neural machine translation models.

The paper introduces XC-Translate, a benchmark for cross-cultural translation, and KG-MT, an end-to-end method that integrates information from multilingual knowledge graphs into machine translation models. The authors demonstrate the effectiveness of their approach in translating texts containing entity names. Their method outperforms state-of-the-art approaches by a large margin.

Based on: Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

HighlightCurated by Aramai Editorial

A Survey of Multi-modal Knowledge Graphs: Technologies and Trends

A comprehensive survey on multi-modal knowledge graphs and their applications.

The paper provides a rigorous definition of multi-modal knowledge graphs (MMKGs) and classifies existing approaches based on four fundamental challenges: representation, fusion, alignment, and translation. It aims to inspire researchers in the field of artificial intelligence by providing a reference for MMKGs. The survey highlights the potential of MMKGs in handling tasks that standard knowledge graphs cannot process.

Based on: A Survey of Multi-modal Knowledge Graphs: Technologies and Trends · ACM Computing Surveys

HighlightCurated by Aramai Editorial

Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT

A case study on constructing a knowledge graph to enhance the performance of large language models in educational question-answering systems.

This paper presents a case study on constructing a cross-data knowledge graph to improve the performance of large language models (LLMs) in educational question-answering systems. The authors propose integrating LLMs with knowledge graphs to provide factual context and address limitations such as remembering events and incorporating new information.

Based on: Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT

HighlightCurated by Aramai Editorial

RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation

A fine-grained evaluation framework for Retrieval-Augmented Generation (RAG) systems.

The paper proposes RAGChecker, a framework that incorporates diagnostic metrics for evaluating RAG systems. It includes a suite of metrics for both retrieval and generation modules, which are verified to have better correlations with human judgments than other evaluation metrics. The authors use RAGChecker to evaluate eight RAG systems and analyze their performance.

Based on: RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking

A novel zero-shot framework integrating community structures with RAG systems to enhance fact-checking.

This paper introduces CommunityKG-RAG, a framework that combines knowledge graphs and retrieval-augmented generation to improve fact-checking. It utilizes multi-hop community structures within KGs to enhance accuracy and relevance of information retrieval. Experimental results show that CommunityKG-RAG outperforms traditional methods in fact-checking.

Based on: CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology

A knowledge graph-based question-answering system for Nanjing Yunjin, a traditional Chinese silk weaving craft.

This paper proposes a question-answering system that integrates knowledge graphs and retrieval augmented generation techniques. The system uses the ROBERTA model to vectorize textual information and the FAISS vector database for efficient storage and retrieval. It aims to overcome limitations of knowledge graph-based systems in terms of updating and semantic understanding.

Based on: Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology · Heritage Science

HighlightCurated by Aramai Editorial

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models

A novel retrieval-augmented generation framework for temporal knowledge graph forecasting using large language models.

The paper proposes GenTKG, a framework that combines temporal logical rule-based retrieval and few-shot parameter-efficient instruction tuning to address challenges in temporal knowledge graph forecasting. Experiments show that GenTKG outperforms conventional methods with low computation resources and limited training data. The work highlights the potential of large language models in the temporal knowledge graph domain.

Based on: GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models