# Knowledge Graphs

StoryWeaver is a unified world model designed for knowledge-enhanced story character customization, aiming to visualize both single and multi-character stories. Based on the AAAI 2025 paper, this model processes character customization and visualization within a unified framework, which is significant for natural language processing and artificial intelligence. Key advantages of StoryWeaver include its ability to handle complex storytelling scenarios and its capacity for continuous updates and feature expansions. The product background information indicates that the model will be regularly updated on arXiv, adding more experimental results.

KAG (Knowledge Augmented Generation) is a specialized framework for domain knowledge services, aimed at leveraging the strengths of knowledge graphs and vector retrieval to mutually enhance large language models and knowledge graphs. It addresses the significant gaps in vector similarity and knowledge reasoning relevance, as well as sensitivity to knowledge logic that are typical issues with Retrieval Augmentation Generation (RAG) techniques. KAG significantly outperforms methods like NaiveRAG and HippoRAG in multi-hop QA tasks; for instance, it achieves a 19.6% relative improvement in F1 scores on hotpotQA and a 33.5% increase on 2wiki. KAG has been successfully applied in two specialized knowledge Q&A tasks at Ant Group, including government and health Q&A, notably improving professionalism compared to RAG methods.

SciAgentsDiscovery is a system that automates scientific research using multi-agent systems and large-scale ontological knowledge graphs. By integrating large language models, data retrieval tools, and multi-agent learning systems, it autonomously generates and refines research hypotheses, revealing potential mechanisms, design principles, and unexpected material properties. The system demonstrates its ability to discover interdisciplinary relationships, particularly in the field of bio-inspired materials, surpassing traditional human-driven research methods.

GraphRAG-Ollama-UI is a local adaptation version of Microsoft's GraphRAG, supporting local model support using Ollama. A interactive user interface is provided through the Gradio UI, making it more convenient for users to manage data, run queries and visualize results. The main advantages of this model include local model support, cost-effectiveness, interactive user interface, real-time graph visualization, file management, settings management, output exploration, and logging.