knowledge graph News and Research

RSS

AI Framework Speeds Up Relay Catalysis Design With Transparent, Literature-Linked Pathways

Researchers from Xiamen University and the University of Edinburgh developed an AI-assisted framework that combines large language models with a catalysis knowledge graph (Cat-KG) to design relay catalysis pathways. The system rapidly finds, explains, and verifies multi-step reaction routes with links to original literature.

26 Aug 2025

New AI Method Boosts Accuracy By Learning From Incomplete Data

Researchers developed LR-GCN, an AI method that improves decision-making by identifying hidden patterns in incomplete data. It boosts predictive accuracy by up to 17%, making AI systems more reliable across real-world applications.

10 Apr 2025

AI Researchers Sharpen Truth Detection with Fact-Level Hallucination Scanner

Researchers have developed FactSelfCheck, a black-box method that detects AI hallucinations at the fact level using sampling and consistency analysis. This fine-grained approach improves correction accuracy by up to 35% without needing external data or model access.

24 Mar 2025

AI Foundation Models Reshape Bioinformatics, Unlocking Genomic and Drug Discovery Advances

Researchers analyzed the latest foundation models (FMs) in bioinformatics, detailing their applications in genomics, proteomics, drug discovery, and single-cell analysis while addressing key challenges like interpretability and AI hallucinations.

24 Feb 2025

Generative AI Transforms Scientific Discovery with Knowledge Graphs

Researcher Markus J. Buehler integrated generative AI and graph theory to uncover interdisciplinary connections, revealing novel insights in bioinspired materials and art-inspired design.

21 Nov 2024

Enhanced Language Models for E-Learning

Researchers have developed an advanced method to augment large language models (LLMs) with domain-specific knowledge for E-learning, significantly improving their performance in generating accurate and contextually relevant content.

26 Jun 2024

LLMs Boosts Scientific Research Discovery

Researchers explored using large language models (LLMs) like GPT-3.5, Llama 2, and Mistral to suggest research properties beyond traditional keywords, aiming to enhance scientific findability. Comparing LLM-generated properties with manually curated ones from the open research knowledge graph (ORKG), they found LLMs promising but recommended further refinement for better alignment with scientific tasks and human expertise

13 Jun 2024

Geological Knowledge Graph Analysis with Graph Attention Networks

This paper introduces a novel method for mining knowledge graph patterns in geological structures using graph attention networks (GAT). By treating subgraph structures as queries and employing an adaptive edge deletion mechanism, the method achieves optimal matching subgraphs.

10 May 2024

LabVantage Introduces a Digitally Native Ecosystem to Boost Speed and Success in R&D Laboratories

LabVantage Solutions, Inc., the leading provider of laboratory informatics solutions and services, including purpose-built LIMS solutions that allow labs to go live faster and at a lower total cost, has made available its semantic search (AILANI), advanced analytics, and LIMS solutions in an integrated, digitally native ecosystem capable of seamlessly supporting R&D laboratory processes.

19 Feb 2024

Empowering Legal Education: AI's Role in International Law

This article outlines a pioneering AI-integrated model for international legal education, aiming to revolutionize traditional teaching methods by leveraging AI's capabilities. The model, employing correlation analysis, AI knowledge mapping, and neural algorithms, promises personalized learning experiences, efficient assessment, and enhanced career prospects for students, as evidenced by its impressive performance in practical teaching evaluations.

18 Feb 2024

Transformative Healthcare: Constructing a Knowledge Graph with Machine Learning

Researchers introduce a pioneering system merging machine learning and knowledge graph technology to streamline medical diagnosis and treatment. Leveraging advanced methodologies like multiple levels refinement and knowledge distillation, the system empowers healthcare professionals with rapid and accurate solutions, offering a transformative tool for navigating complex medical research. Through iterative refinement and interactive exploration, this system provides comprehensive and relevant information, addressing key challenges in healthcare knowledge management.

9 Feb 2024

MMSS_MKR Framework Unveils the Future of Music Recommendations

The MMSS_MKR framework revolutionizes music recommendation systems by integrating knowledge graphs and multi-task learning approaches. Offering robust solutions to data sparsity and cold start issues, this innovative model, combining prediction techniques and enhanced loss functions, outperforms existing methodologies. The study not only presents significant improvements in music recommendation accuracy but also outlines promising avenues for future exploration.

1 Feb 2024

A Framework for Distributed Self-Driving Laboratories in the World Avatar Project

This paper unveils a revolutionary conceptual architecture for distributed self-driving laboratories (SDLs) within the World Avatar Project, enabling global collaboration in scientific research. Through ontologies, autonomous agents, and a dynamic knowledge graph, the framework orchestrates experimentation workflows, exemplified in collaborative closed-loop optimization for a pharmaceutically relevant reaction. The architecture liberates scientists from routine tasks, redefines closed-loop optimization, and proposes a transformative approach for authentic distributed SDLs, marking a significant stride towards the future of autonomous and integrated laboratory workflows.

31 Jan 2024

OmniEvent: A Comprehensive Toolkit for Event Understanding in Text

OmniEvent is an innovative toolkit for event understanding in text, addressing event detection (ED), event argument extraction (EAE), and event relation extraction (ERE). It offers a comprehensive, fair, and user-friendly approach, supporting various mainstream models and datasets while providing solutions to common evaluation pitfalls, making it a valuable tool in natural language processing research.

28 Sep 2023

Knowledge-Boosted Ensembles: Enhancing Language Model Reliability

Researchers introduce a novel method that combines reinforcement learning and external knowledge integration to create an ensemble of language models, surpassing individual models in accuracy and prediction certainty, thereby enhancing language processing capabilities.

30 Aug 2023

MultiBART-GAT: Enhancing Abstractive Summarization with Knowledge Graphs

Researchers propose MultiBART-GAT, an encoder-decoder architecture model based on BART, for abstractive summarization. By incorporating knowledge graph information and structured semantics, the model improves factual correctness and generates higher-quality summaries, as demonstrated through evaluation on the Wiki-Sum dataset.

6 Jul 2023