knowledge graph
PulseAugur coverage of knowledge graph — every cluster mentioning knowledge graph across labs, papers, and developer communities, ranked by signal.
- used by graph neural networks 80%
- used by Gotit.pub 70%
- used by alphaXiv 70%
- used by CatalyzeX 70%
- used by CatalyzeX Code Finder for Papers 70%
- used by Influence Flower 70%
- used by CORE Recommender 70%
- used by Graphrag 70%
- used by Litmaps 70%
- uses Graphrag 70%
- used by ontology 70%
- developed by graph neural networks 70%
- 2026-05-19 research_milestone A new paper proposes a framework for inferring and defending against sensitive attribute inference from knowledge graph embeddings. source
17 day(s) with sentiment data
-
New FrED framework estimates external data influence on AI models
Researchers have developed a new probabilistic framework called FrED to estimate the influence of external data on generative AI models. This black-box method uses a combination of feature similarities and domain-specif…
-
LLM-powered framework enhances STI analytics with dynamic knowledge graphs
This paper introduces a novel framework that combines large language models (LLMs) with dynamic knowledge graphs and traditional bibliometrics to enhance the analysis of science, technology, and innovation (STI). The pr…
-
Arabic knowledge graph outperforms English for implicit aspect identification
A new study published on arXiv compares the effectiveness of language-specific versus cross-lingual knowledge graphs for identifying implicit aspects in Arabic text. The research found that a native Arabic knowledge gra…
-
DeLIVeR framework enhances LLM fact-checking with knowledge graph exploration · 1 source tracked
Researchers have developed DeLIVeR, a new framework designed to improve the accuracy of automated fact-checking by large language models. This system decomposes complex claims into targeted questions, which are then use…
-
Survey details GNN-based link prediction techniques and applications
This paper offers a comprehensive survey of Graph Neural Network (GNN)-based link prediction techniques. It introduces a new taxonomy to categorize advancements by GNN encoder architectures, such as GCN-based, GAE-based…
-
New HG-RAG framework enhances LLMs with structured knowledge graph navigation
A new framework called HG-RAG has been developed to enhance the capabilities of Large Language Models (LLMs) by integrating structured knowledge graphs. Unlike traditional RAG systems that use flat document stores, HG-R…
-
MARS system integrates LLMs with knowledge graphs for KGQA without fine-tuning
Researchers have developed MARS, a novel approach for knowledge graph question answering (KGQA) that integrates large language models (LLMs) with knowledge graphs (KGs) without requiring model fine-tuning. MARS employs …
-
Neurosymbolic AI & Knowledge Graphs Researcher Wanted
A research position is open for individuals interested in neurosymbolic AI and knowledge graphs. The role involves working on the Platform MaterialDigital project and requires expertise in ontologies and large language …
-
Survey details GNN applications across knowledge graph technologies
This paper provides a comprehensive survey of how Graph Neural Networks (GNNs) are applied to knowledge graph technologies. It introduces a novel taxonomy that categorizes GNN-based KG methods across the entire KG pipel…
-
New framework KGCQual offers interpretable evaluation for knowledge graphs
Researchers have introduced KGCQual, a new framework designed to evaluate the quality of knowledge graphs constructed from text. This interpretable metric assesses both entity-level completeness and relation-level seman…
-
New method fuses graph and text for patent entity alignment
This paper introduces a novel method for aligning entities within science and technology patent knowledge graphs. The proposed approach leverages a graph convolution network combined with the BERT model to fuse structur…
-
AI-generated knowledge graphs can be validated using SHACL
This article discusses methods for ensuring the quality of AI-generated knowledge graphs, particularly those using RDF triples. It highlights the challenge of scaling manual human review and proposes using SHACL (Shapes…
-
New KGCQual metric offers interpretable evaluation for knowledge graph construction
Researchers have introduced KGCQual, a new framework designed to evaluate the quality of knowledge graphs (KGs) automatically constructed from text. This metric offers an interpretable assessment of KG fidelity by compa…
-
New MC-RAG System Enhances Retrieval for Complex Multi-Constraint Queries
Researchers have developed MC-RAG, a novel retrieval-augmented generation (RAG) system designed to handle complex queries with multiple constraints. Unlike traditional RAG systems that struggle with such queries, MC-RAG…
-
Knowledge Graphs and Explainable AI Enhance Urban Mining Audits
This paper explores the integration of knowledge graphs (KGs) and explainable AI (XAI) to enhance decision-making in urban mining, particularly for pre-demolition assessments. The authors propose that combining these AI…
-
AgentKGV framework enhances knowledge graph fact verification with two-stage training
Researchers have developed AgentKGV, a novel framework designed to improve the accuracy and efficiency of fact-checking knowledge graphs. This agentic LLM-RAG system employs a two-stage training strategy, combining turn…
-
Paper details knowledge graph construction for academic conference data
This paper explores the application of deep learning and knowledge graph technology to analyze scientific and technological academic conference data. It details key techniques such as named entity recognition, semantic …
-
New paper proposes knowledge graphs for detailed scientific resource portraits
A new paper proposes a method for creating detailed representations of scientific resources by integrating knowledge graph technology, text representation learning, and entity extraction. The authors highlight the explo…
-
InductWave paper introduces inductive logical query answering for large knowledge graphs
Researchers have introduced InductWave, a novel wavelet-based embedding method designed for inductive multi-hop logical query answering on large knowledge graphs. Unlike transductive methods that require all entities to…
-
New research adapts LLMs for social sciences and humanities scholarship
A new research paper explores the adaptation of Large Language Models (LLMs) for scholarly work in the Social Sciences and Humanities (SSH). The study focuses on integrating knowledge graphs and multilingual corpora to …