knowledge graph
PulseAugur coverage of knowledge graph — every cluster mentioning knowledge graph across labs, papers, and developer communities, ranked by signal.
- 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 benchmark KGI-Bench evaluates knowledge graph data integration pipelines
Researchers have introduced KGI-Bench, a new benchmark designed to evaluate the effectiveness of pipelines used for integrating data into knowledge graphs. This benchmark utilizes three quality metrics: coverage, correc…
-
New method Ex-GraphRAG deciphers LLM evidence routing from knowledge graphs
Researchers have developed Ex-GraphRAG, a novel method for interpreting how Large Language Models (LLMs) use information from knowledge graphs. This new approach replaces the standard Graph Neural Network encoder with a…
-
KAPPS architecture uses knowledge graph for circular manufacturing
Researchers have developed KAPPS, a novel knowledge-based architecture designed for circular manufacturing systems. This architecture addresses the challenges of handling heterogeneous materials and dynamic processes in…
-
AI transforms cloud system testing with intelligent, automated approaches
Traditional software testing methods are insufficient for modern, AI-integrated cloud systems that learn and adapt over time. These systems are event-driven and produce variable outputs based on context, making determin…
-
AI question probes life's hardest categories for formal mapping
The user is asking a question about the difficulty of mapping aspects of life into formal systems, specifically within the context of AI, knowledge representation, and semantic web technologies. The question probes whic…
-
SciAtlas knowledge graph aids AI in navigating 43M academic papers
Researchers have introduced SciAtlas, a large-scale knowledge graph designed to help AI agents navigate the overwhelming volume of academic research. By integrating over 43 million papers across 26 disciplines, SciAtlas…
-
New framework tackles privacy risks in knowledge graph embeddings
Researchers have developed a framework to identify and mitigate privacy risks in knowledge graph embeddings (KGEs). The study demonstrates how adversaries can infer sensitive user attributes from KGE outputs, even when …
-
LLM tutors fail at crucial feedback, study finds
A new benchmark evaluating LLM tutoring agents reveals significant weaknesses in their ability to provide effective feedback. Researchers found that while LLMs perform well on identifying optimal solutions, they frequen…
-
AI question prompts users to map life connections via knowledge graphs
This post on Mastodon poses a question about knowledge graphs, asking users to imagine their lives as such and identify two unlikely entities with strong connections. It frames this within the context of semantic web te…
-
PersonalAI 2.0 enhances LLMs with knowledge graphs and planning
Researchers have developed PersonalAI 2.0 (PAI-2), a new framework that improves large language model (LLM) systems by integrating external knowledge graphs. PAI-2 employs a dynamic, multistage query processing pipeline…
-
MAGE framework uses knowledge graphs for self-evolving AI agents
Researchers have developed MAGE, a framework that uses a co-evolutionary knowledge graph to manage self-evolving language model agents. This approach externalizes the agent's knowledge into a graph, allowing it to learn…
-
SPARK framework uses knowledge graphs for AI self-play in scientific literature
Researchers have introduced SPARK, a novel framework that leverages knowledge graphs to enhance self-play reinforcement learning for scientific literature analysis. SPARK constructs a unified knowledge graph from multip…
-
Researchers propose graphlets as structural tokens for knowledge graph foundation models
Researchers have developed a novel framework for Knowledge Graph Foundation Models (KGFMs) that utilizes graphlets as structural tokens. This approach addresses the challenge of transferring representations across diver…
-
Graph-augmented LLMs improve Swiss MP ideology prediction using knowledge graphs
Researchers have developed a new framework called PG-RAG that enhances Large Language Models (LLMs) for predicting the political ideology of Swiss Members of Parliament. This approach integrates information from politic…
-
New hybrid microservice uses KG-first, LLM-fallback for skill search
Researchers have developed a novel microservice called SkillGraph-Service to address the complexity of integrating labor market competency frameworks like ESCO and O*NET into educational systems. The service employs a h…
-
GNNs create hierarchy-aware knowledge graph embeddings for yeast phenotype prediction
Researchers have developed a novel method using graph neural networks (GNNs) to create hierarchy-aware embeddings for knowledge graphs. This approach incorporates semantic loss derived from ontologies to better represen…
-
AI co-clinicians using knowledge graphs to reduce diagnostic errors by 30%
An AI co-clinician system, utilizing knowledge graphs, is set to revolutionize medical follow-up and decision support by 2026. This technology aims to enhance diagnostic accuracy and personalize patient care, with resea…
-
OntoLogX uses LLMs to extract actionable threat intelligence from cybersecurity logs
Researchers have developed OntoLogX, an AI agent designed to extract Cyber Threat Intelligence (CTI) from raw cybersecurity logs. The system utilizes Large Language Models (LLMs) combined with a lightweight log ontology…
-
Researchers build knowledge graphs from sparse autoencoder features for model interpretability
Researchers have developed a method to transform sparse autoencoder (SAE) features into structured knowledge graphs. This process involves creating a domain-specific concept universe from SAE features and then building …
-
Researchers develop new methods for knowledge graph retrieval and completion
Researchers have developed new frameworks to enhance knowledge graph completion and visual question answering by integrating multimodal knowledge graphs with retrieval-augmented generation techniques. One approach, RADD…