From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
This is an incremental survey paper that synthesizes existing research on integrating structured knowledge with language models for researchers and practitioners in AI.
This survey paper systematically examines the synergy between Knowledge Graphs (KGs) and Large Language Models (LLMs), categorizing approaches into KG-enhanced LLMs for improved reasoning and LLM-augmented KGs for construction and querying, while identifying gaps and proposing future directions like neuro-symbolic integration.
Integrating structured knowledge from Knowledge Graphs (KGs) into Large Language Models (LLMs) enhances factual grounding and reasoning capabilities. This survey paper systematically examines the synergy between KGs and LLMs, categorizing existing approaches into two main groups: KG-enhanced LLMs, which improve reasoning, reduce hallucinations, and enable complex question answering; and LLM-augmented KGs, which facilitate KG construction, completion, and querying. Through comprehensive analysis, we identify critical gaps and highlight the mutual benefits of structured knowledge integration. Compared to existing surveys, our study uniquely emphasizes scalability, computational efficiency, and data quality. Finally, we propose future research directions, including neuro-symbolic integration, dynamic KG updating, data reliability, and ethical considerations, paving the way for intelligent systems capable of managing more complex real-world knowledge tasks.