HighlightCurated by Aramai EditorialarXiv (Cornell University)

Knowledge Prompting: How Knowledge Engineers Use Large Language Models

A study on the use of large language models in knowledge engineering.

The paper explores how knowledge engineers utilize large language models to support semi-automatic tasks. A multimethod study was conducted during a KE hackathon to investigate participants' views, challenges, and skills needed for integrating LLMs into their practices. The findings highlight the potential of prompting as a valuable skill for knowledge engineers working with LLMs.

Based on: Knowledge Prompting: How Knowledge Engineers Use Large Language Models · arXiv (Cornell University)

HighlightCurated by Aramai EditorialProceedings of the AAAI Conference on Artificial Intelligence

Graph Neural Prompting with Large Language Models

A novel plug-and-play method to enhance pre-trained large language models using knowledge graphs.

The paper proposes Graph Neural Prompting (GNP), a method to assist LLMs in learning beneficial knowledge from KGs. GNP includes various designs, such as a graph neural network encoder and a cross-modality pooling module. Experiments demonstrate the superiority of GNP on commonsense and biomedical reasoning tasks across different LLM sizes.

Based on: Graph Neural Prompting with Large Language Models · Proceedings of the AAAI Conference on Artificial Intelligence

HighlightCurated by Aramai EditorialACM Computing Surveys

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 Editorialopenalex.org

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 EditorialarXiv (Cornell University)

WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs

A paper proposing a new approach to integrating web search and knowledge graphs into retrieval-augmented generation systems.

The authors propose WeKnow-RAG, a system that combines knowledge graphs with dense vector retrieval to improve the accuracy and reliability of large language models. The approach utilizes domain-specific knowledge graphs and multi-stage web page retrieval techniques to enhance performance on factual information and complex reasoning tasks. A self-assessment mechanism is also integrated to evaluate the trustworthiness of generated answers.

Based on: WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs · arXiv (Cornell University)

HighlightCurated by Aramai Editorialdoi.org

Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning

A method called SPIRES is available as part of the open source OntoGPT package.

SPIRES is a method that uses zero-shot learning to populate knowledge bases. It is part of the OntoGPT package, an open-source tool. The method's purpose and functionality are not further described in the provided snippet.

Based on: Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning

HighlightCurated by Aramai EditorialarXiv (Cornell University)

Construction of Knowledge Graphs: State and Challenges

A research paper on the construction and updating of knowledge graphs.

The authors discuss graph models, requirements for KG construction pipelines, and necessary steps to build high-quality KGs. They evaluate the state-of-the-art and identify areas in need of further research. The paper provides an overview of the individual steps involved in creating and updating KGs from unstructured and structured data sources.

Based on: Construction of Knowledge Graphs: State and Challenges · arXiv (Cornell University)

HighlightCurated by Aramai EditorialArtificial Intelligence Review

Knowledge Graphs: Opportunities and Challenges

A systematic overview of knowledge graphs, focusing on opportunities and challenges.

This paper presents a comprehensive review of knowledge graphs, discussing their applications in AI systems and potential fields. It also explores technical challenges such as knowledge graph embeddings, acquisition, completion, fusion, and reasoning. The authors aim to provide insights for future research and development in the field.

Based on: Knowledge Graphs: Opportunities and Challenges · Artificial Intelligence Review

HighlightCurated by Aramai EditorialVBN Forskningsportal (Aalborg Universitet)

Knowledge Graph Exploration Systems: are we lost?

A position paper on the challenges and requirements for effective knowledge graph exploration systems.

The authors discuss the limitations of current knowledge graph data management systems in meeting the needs of KG exploration use cases. They present an overview of state-of-the-art approaches, identify unmet requirements, and highlight promising research directions.

Based on: Knowledge Graph Exploration Systems: are we lost? · VBN Forskningsportal (Aalborg Universitet)

HighlightCurated by Aramai EditorialIEEE Transactions on Neural Networks and Learning Systems

A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

Comprehensive review of knowledge graph research topics and recent breakthroughs.

The paper provides a survey of knowledge graphs, covering representation learning, acquisition, and applications.,It reviews various aspects of knowledge graph embedding, including representation space, scoring function, encoding models, and auxiliary information.,The authors also explore emerging topics such as metarelational learning, commonsense reasoning, and temporal knowledge graphs.

Based on: A Survey on Knowledge Graphs: Representation, Acquisition, and Applications · IEEE Transactions on Neural Networks and Learning Systems

HighlightCurated by Aramai EditorialACM Computing Surveys

Knowledge Graphs

Comprehensive introduction to knowledge graphs.

The article provides an overview of knowledge graphs, their applications, and challenges.,It motivates and contrasts various graph-based data models and query languages.,The authors explain how knowledge can be represented and extracted using deductive and inductive techniques.

Based on: Knowledge Graphs · ACM Computing Surveys

HighlightCurated by Aramai Editorialopenalex.org

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

This paper presents a method for question answering with knowledge bases using staged query graph generation.

The authors propose a semantic parsing approach that generates query graphs in stages to answer questions based on a knowledge base. This method improves the accuracy of question answering by iteratively refining the query graph. The proposed approach is evaluated on several benchmarks and shows competitive results compared to state-of-the-art methods.

Based on: Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base