#Knowledge Graphs

This document objectively explores Retrieval-Augmented Generation (RAG) methodologies, detailing patterns, dialogue routing, LLM models, and retrieval techniques, including vector retrieval and chunking strategies. Advanced prompting strategies, like multi-modal and multi-document approaches, are analyzed alongside issues of hallucination and guardrails. It also addresses evaluation metrics, performance optimization, privacy concerns, and security threats. The document discusses practical applications such as chatbots and tools like HayStack and Langchain, and provides vendor-specific examples such as Elasticsearch + OpenAI, focusing on optimizing RAG systems for efficient and secure production use.

Examine an innovative framework that merges Large Language Models (LLMs) with Knowledge Graphs (KGs) to enable precise and explainable reasoning. The framework employs a planning-retrieval-reasoning sequence, using KGs to develop authentic plans that help generate interpretable outcomes. Access automated resources such as pre-trained weights and datasets for easy integration, and investigate plug-and-play reasoning with multiple LLMs. Suitable for developers looking to improve machine reasoning functionalities while maintaining transparency and accuracy.

Discover how Large Language Models (LLMs) and Knowledge Graphs (KGs) integrate to improve reasoning and knowledge access. This project aggregates important studies and resources that aim to bring together LLMs with KGs for more effective factual data utilization. LLMs perform well in diverse scenarios, yet they often miss the detailed factual knowledge that KGs provide. This resource presents methods to integrate LLMs and KGs, addressing challenges in knowledge retention and access. Core areas include KG-enhanced LLMs, LLM-augmented KGs, and combined approaches utilizing both technologies. Follow the latest in research developments, including graph-constrained and temporal KG reasoning, as recognized by conferences like NeurIPS and ACL.

Use large language models to transform Wikipedia pages into knowledge graphs in formats such as GraphML, GEXF, and HTML. Leveraging ChatGPT and a range of models via LiteLLM, this tool offers customizable prompts, efficient cache support, and affordable token usage. Suitable for generating insights into entity types and relationships in digital knowledge spaces, compatible with Google Colab and Python environments.

An extensive collection of papers and tools showcases the integration of large language models (LLMs) in recommender systems, covering aspects from feature engineering to personalized recommendations. The project features a survey paper accepted by ACM Transactions on Information Systems, which delves into the latest advancements in LLM-enhanced recommender systems. Regular updates ensure it remains a comprehensive resource for understanding the synergy between LLMs and recommendation technologies.

This repository provides a comprehensive collection of academic papers on the integration of Knowledge Graphs (KGs) and Large Language Models (LLMs). It is a valuable resource for researchers and practitioners interested in advancing domain-specific applications, improving question answering, and enhancing reasoning through seamless KG-LLM integration. Contributions are welcomed via Issues or Pull Requests to expand this growing database. Stay informed about the latest advancements, preprints, and surveys on KG and LLM interactions. Explore resources aimed at minimizing hallucinations, improving retrieval, and enhancing factuality in AI solutions.