Vietnamese legal ontology traces citations to dated law versions
Of 67,868 cited provisions, 61,487 resolve to a dated law version and 19,012 match word for word.
Stories per day · 30 days
1 RSS
Relatedretrieval-augmented-generation2ai-agents1apple-intelligence1citations1data-integration1dermatology1design-science1edge-ai1enterprise-data1exaforce1flood-detection1grafana1hallucination1incident-response1legal-ontology1llm1macos1medical-ai1
22 stories, newest first · one card per story
Stories tagged #knowledge-graph
Every Mac since 2022 includes undocumented family classifier
Apple Intelligence builds a personal knowledge graph on Macs including family relationships from device data like contacts and photos.
1
SkinMind uses graph probing for dermatology retrieval-augmented generation
Authors report average gains of 8.70 and 8.89 points with GPT-5.4-mini and Gemini-2.5-Flash on six VQA benchmarks.
KG-RAG4SM retrieves knowledge-graph subgraphs for schema matching
Authors report precision gains of 39.79% on MIMIC and 69.20% on Synthea versus named prior methods, without retraining.
HydroReasoner advances floodwater detection with knowledge-guided reasoning
HydroReasoner uses Qwen2.5-VL and a floodwater knowledge graph to improve reasoning and generalize to varied scenes while running efficiently on edge devices.
Exaforce argues SOCs are letting AI act sooner than expected
The author cites Invisible Technologies cutting mean time to investigate by 95 percent after adopting Exaforce, and urges evidence-backed, bounded autonomy.
Grafana Cloud adds Knowledge Graph for agents and incident response
Custom entities and agent runtime context are generally available; several monitoring features remain in preview.
1
Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs
A knowledge-graph layer resolves imperfect enterprise prompts better than schema-only semantic matching.
KGATE : a Knowledge Graph Embedding Training Environment
KGATE is a modular PyTorch library for training knowledge-graph autoencoders with leakage-controlled preprocessing and reproducible benchmarks.
PrivDev: Mapping Static-Analysis Data Types to DPV
PrivDev maps 122 Bearer CLI static-analysis data types to DPV personal-data categories and GDPR provisions via deterministic matching plus an LLM.
An ontology for cross-sectoral crisis management: core and public health modules
ECMO, a modular OWL ontology, standardizes cross-sector crisis data including a SNOMED-aligned public health module.
Link Inference Attack on Privacy-Preserving Knowledge Graphs
A topology-based link inference attack recovers hidden knowledge-graph relations that edge deletion was assumed to protect.
Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
Nutri-ATLAS grounds nutrition advice in USDA graphs, hybrid retrieval, and robot-observed food availability.
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
Researchers build CodeGraph, a 158-million-node open-taxonomy knowledge graph of source code grounded in Wikidata.
Making global data easier to explore
UN launches AI-ready UN System Data Commons built on Google's Data Commons, unifying global statistics with natural-language search and MCP support.
1
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
GraphProfiler links LLM attribute inferences to source posts via personal knowledge graphs, enabling targeted redaction of privacy-leaking content.
An Evidence-First Multi-LLM Framework for Auditable Critical-Infrastructure Dependency Modeling
Evidence-first multi-LLM framework builds auditable critical-infrastructure dependency graphs while preserving provenance and unresolved cases.
The Intelligible World of Agents
Recorded Future argues cybersecurity AI agents perform better when reasoning over structured, curated intelligence graphs rather than fragmented alerts or open-source noise.
2
Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support
A retrospective study found GPT-4 over-flagged emergency department revisit cases while an LLM knowledge-graph screener achieved 83-100% positive predictive value.
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
Training-free reasoning-plus-retrieval framework lifts multilingual multimodal entity linking accuracy by 6.9% overall and up to 23.3% on rare entities.
Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports
AHLERT generates environment-aware threat hunting leads from CTI reports using ATT&CK-seeded knowledge graph retrieval, roughly doubling F1 over flat-RAG baselines.
Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability
A controlled study finds agent memory portability varies sharply: fixed-schema knowledge graphs survive model swaps while compressed notes degrade.