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
15 day(s) with sentiment data
-
Scholarly knowledge graphs tackle source attribution with new provenance model
This paper introduces a new approach to building scholarly knowledge graphs by addressing the complexities of source attribution and comparability. It proposes distinguishing between a working address for evidence retri…
-
New ThreadRAG framework improves RAG with semantic topology and energy pathfinding
Researchers have introduced ThreadRAG, a novel framework designed to enhance retrieval-augmented generation (RAG) by addressing semantic loss and modality mismatch issues. ThreadRAG utilizes a Semantic Topology Mapper t…
-
Netflix builds end-to-end knowledge graph for observability
Netflix has detailed its approach to ontology-driven observability, a system designed to create an end-to-end knowledge graph for its operations. This system aims to enhance how the company monitors and understands its …
-
Decision4Rec framework integrates decision models into recommender systems
Researchers have developed Decision4Rec, a novel framework designed to integrate decision models into recommender systems. This framework utilizes knowledge graphs and active graphs to log recommendation scenarios and e…
-
Knowledge graphs enhance enterprise data assistants' handling of imperfect prompts
Researchers have developed and evaluated a knowledge graph-based mediation system designed to improve how enterprise data assistants handle imperfect user prompts. In a simulation using real-world data from a CFO unit, …
-
Company Brain launches AI knowledge assistant for organizations
Company Brain has developed an AI-powered knowledge assistant designed to help organizations manage and access their internal information more efficiently. The platform utilizes AI agents and a knowledge graph to allow …
-
AI architecture crafts personalized stories for older adults
Researchers have developed a novel hybrid AI architecture designed for personalized storytelling aimed at older adults. This system integrates knowledge graphs, user modeling, and argumentation theory to create narrativ…
-
AI models enhanced for legal reasoning using knowledge graphs · 2 sources tracked
Two new research papers explore enhancing legal reasoning in AI models by integrating knowledge graphs. The first paper proposes a structure-driven knowledge graph approach for verifiable retrieval in legal contexts, fo…
-
Oleksandra Bruns defends PhD thesis on temporal modeling in knowledge graphs
Oleksandra Bruns has successfully defended her PhD thesis titled "Choosing the Right Time: Guidelines for Temporal Modeling in Knowledge Graphs" at the Karlsruhe Institute of Technology (KIT). This milestone marks a sig…
-
SPARQL-LLM tops TEXT2SPARQL 2026 challenge with multilingual KGQA
A new open-source system called SPARQL-LLM has achieved first place in the TEXT2SPARQL 2026 challenge, outperforming eight other approaches. This system excels at translating natural language questions into SPARQL queri…
-
New system DAG-EDA aids LLM-analyst collaboration in data exploration
Researchers have developed DAG-EDA, a system designed to enhance exploratory data analysis (EDA) by facilitating collaboration between analysts and large language models (LLMs). The system utilizes an intent graph to br…
-
New framework enhances semantic table interpretation and data quality assessment
Researchers have developed an explainable framework focused on header-centric interpretation for large-scale semantic tables and data quality assessment. This system, called HeadersIQ, maps column headers to 39 interpre…
-
New research tackles knowledge graph embedding challenges and uncertainty
Two new arXiv papers delve into the complexities of knowledge graph embedding (KGE) and representation learning. The first paper introduces KGATE, a modular Python library designed to streamline the training and compari…
-
New RoP Framework Enhances Knowledge Graph Question Answering Accuracy
Researchers have developed a new framework called Reward on Path (RoP) to improve the accuracy of Knowledge Graph Question Answering (KGQA) models. This method learns an intermediate supervision signal from answer label…
-
New Foresight-over-Graph framework boosts LLM knowledge base question answering
Researchers have introduced Foresight-over-Graph (FoG), a novel framework designed to enhance knowledge base question answering (KBQA) by improving how large language models (LLMs) retrieve and utilize information from …
-
AI improves medical device defect detection using uncertainty awareness
Researchers have developed a machine learning framework that uses epistemic uncertainty to improve defect detection in medical device manufacturing. By representing manufacturing and device report data with Knowledge Gr…
-
Dissertation details AI for structured knowledge retrieval and reasoning
This dissertation introduces a novel architecture for transforming unstructured domain-specific text into structured knowledge for retrieval and reasoning. It presents Binary Bleed, an adapted binary search method for N…
-
Context Engineering: The Next Frontier Beyond Naive RAG
The article argues that current Retrieval-Augmented Generation (RAG) systems, often referred to as 'naive RAG,' are insufficient for enterprise-level AI applications due to their focus on simple retrieval rather than ro…
-
SPRIG integrates Semantic IDs and KG paths for efficient generative recommendation
Researchers have introduced SPRIG, a novel generative recommender system that integrates content-derived Semantic IDs (SIDs) with knowledge graph (KG) path reasoning. This approach aims to combine the relational groundi…
-
New connector streamlines Typeform data for AI knowledge graphs
A new connector has been developed to streamline the ingestion of Typeform survey responses into AI applications, specifically for use with Cognee's knowledge graph and retrieval-augmented generation (RAG) pipelines. Th…