Knowledge Tree
Knowledge graph-enhanced large language models
Also known as: kg-llm, Knowledge graph-enhanced Large Language Models, Knowledge graph large language model, Knowledge-graph-enhanced Large Language Models, KG-enhanced LLMs, Knowledge Graph-enhanced Large Language Models, knowledge-graph-powered Large Language Models, Knowledge graph-augmented language models, Knowledge graph-enhanced Large Language Model
Facts (27)
Sources
Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org 11 facts
claimThere are three primary strategies for fusing Knowledge Graphs and Large Language Models: LLM-Enhanced KGs (LEK), KG-Enhanced LLMs (KEL), and Collaborative LLMs and KGs (LKC).
referenceThe study 'Practices, opportunities and challenges in the fusion of knowledge' identifies three approaches for integrating knowledge graphs and Large Language Models: KG-enhanced LLMs (KEL), LLM-enhanced KGs (LEK), and collaborative LLMs and KGs (LKC).
claimTraditional knowledge graphs are static snapshots that lack mechanisms to represent temporal dependencies or model dynamic updates, which causes knowledge graph-enhanced large language models to struggle with reasoning over sequences of events, causal relationships, or time-sensitive information.
claimThe fusion of Knowledge Graphs (KGs) and Large Language Models (LLMs) is categorized into three primary strategies: KG-enhanced LLMs (KEL), LLM-enhanced KGs (LEK), and collaborative LLMs and KGs (LKC).
claimThe lack of integrated multimodal knowledge hinders knowledge graph-enhanced Large Language Models in performing tasks that require cross-modal understanding in domains such as healthcare, autonomous driving, and robotics.
claimExisting explainability techniques applied to knowledge graph-enhanced large language models often offer only shallow insight and lack user-centered interpretability, according to Yinxin et al. (2024).
claimKnowledge graph-enhanced large language models improve conversational agents in healthcare by providing structured medical knowledge, which allows for more informed responses during patient interactions.
claimOptimization methods for knowledge graph-enhanced large language models, such as graph pruning, caching, and approximate retrieval, either compromise accuracy or fail to scale well with large graphs and multi-user environments, according to Guo et al. (2022).
claimKnowledge graph-enhanced Large Language Models (LLMs) lack access to comprehensive structured support when dealing with emerging diseases, rare events, or complex procedures.
referenceLiu et al. (2024) proposed a method for knowledge graph-enhanced large language models via path selection in the preprint 'Knowledge graph-enhanced large language models via path selection'.
claimKnowledge graph-enhanced large language models often incur high computational overhead due to the necessity of graph traversal, entity linking, and dynamic retrieval during inference, which introduces latency that hinders deployment in real-time applications like dialogue systems, autonomous agents, and online recommendation.
A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Nov 4, 2024 6 facts
claimInterpretability research in KG-enhanced LLMs uses knowledge graphs to understand the knowledge learned by LLMs and to interpret their reasoning processes.
referenceKG-enhanced LLMs focus on enhancing LLM performance and interpretability using KGs, while LLM-augmented KGs aim to improve KG-related tasks with the help of LLMs.
claimPre-training methods for KG-enhanced LLMs incorporate knowledge graphs during the LLM training phase to enhance knowledge expression.
claimKG-enhanced LLMs are categorized into three research areas: pre-training, inference, and interpretability.
claimInference methods for KG-enhanced LLMs utilize knowledge graphs during the LLM inference phase to access the latest knowledge without requiring retraining.
claimKG-Enhanced LLM integration involves embedding a Knowledge Graph into a Large Language Model to improve performance and address issues such as hallucination or lack of interpretability.
Leveraging Knowledge Graphs and LLM Reasoning to Identify ... arxiv.org Jul 23, 2025 3 facts
claimLi et al. (2024) proposed the use of Knowledge Graph-enhanced Large Language Models (KG-enhanced LLMs) for domain-specific question answering systems in technical fields.
claimThe application of Knowledge Graph-Large Language Model (KG-LLM) systems to analyze Discrete Event Simulation (DES) output data for operational insights, such as iterative bottleneck diagnosis and root cause analysis, remains largely unexplored.
referenceKG-enhanced LLMs leverage Knowledge Graphs during pre-training or inference time, with Retrieval-Augmented Generation (RAG) being a prominent technique that uses external sources to inform LLM generation, as described by Muneeswaran et al. (2024).
Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org Jul 9, 2024 2 facts
referencePriyanka Sen, Sandeep Mavadia, and Amir Saffari authored the 2023 paper 'Knowledge graph-augmented language models for complex question answering', presented at the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE).
claimYang et al. demonstrated that knowledge graph-enhanced pre-trained language models (KGPLMs), which inject a knowledge encoder module into pre-trained language models, consistently exhibit longer running times than vanilla LLMs like BERT across pre-training, fine-tuning, and inference stages.
Unknown source 1 fact
claimKnowledge-graph-enhanced Large Language Models (KG-enhanced LLMs) merge the strengths of structured knowledge graphs and unstructured language models to enable AI systems to achieve higher capabilities.
Large Language Models Meet Knowledge Graphs for Question ... arxiv.org Sep 22, 2025 1 fact
referenceLi et al. (2024b) developed a framework for knowledge graph-enhanced large language models that utilizes question decomposition and atomic retrieval, published in EMNLP Findings (pages 11472–11485).
(PDF) Combining Knowledge Graphs and Large Language Models researchgate.net Jul 9, 2024 1 fact
claimThe authors of the paper 'Combining Knowledge Graphs and Large Language Models' collected 28 papers that outline methods for knowledge-graph-powered Large Language Models (LLMs), LLM-based knowledge graphs, and LLM-knowledge graph hybrid approaches.
KG-enhanced LLM: Large Language Model (LLM) and Knowledge ... medium.com Oct 8, 2025 1 fact
claimKnowledge Graph-enhanced Large Language Models combine the strengths of large language models with structured knowledge from knowledge graphs to improve performance.
KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org Mar 18, 2025 1 fact
referenceDong Shu, Tianle Chen, Mingyu Jin, Yiting Zhang, Mengnan Du, and Yongfeng Zhang authored 'Knowledge graph large language model (kg-llm) for link prediction', published as an arXiv preprint (arXiv:2403.07311).