TY - CHAP
T1 - Future Innovations in Combining Large Language Models and Knowledge Graphs
AU - Dobriy, Daniel
PY - 2026/11/6
Y1 - 2026/11/6
N2 - This chapter examines how large language models and knowledge graphs can be integrated to support factual grounding, traceable reasoning, and persistent, updatable knowledge. It develops a taxonomy covering graph-grounded retrieval and generation, KG construction, access and maintenance, and hybrid adaptive architectures. It reviews evaluation resources, emphasizing the need to assess graph access, evidence retrieval, updating, provenance, uncertainty, memory stability, and computational cost separately. Particular attention is given to graph-based agent memory, where KGs support persistent knowledge, world modeling, inference, tool and agent coordination, and governance of shared assertions. A running example of a scientific literature analyst illustrates these capabilities and their operational requirements. The chapter identifies key challenges in graph versioning, runtime logical validation, executable graph access, source discovery, and metadata interoperability. It outlines three future directions: data search engines combining natural-language interaction with federated querying over the decentralized Web of Data, a common semantic layer connecting diverse knowledge organization systems, and generative models that operate directly on language-independent semantic representations. It argues that the value of integration depends on task requirements and on maintaining graph memory that is accurate, auditable, reversible, and governable over time.
AB - This chapter examines how large language models and knowledge graphs can be integrated to support factual grounding, traceable reasoning, and persistent, updatable knowledge. It develops a taxonomy covering graph-grounded retrieval and generation, KG construction, access and maintenance, and hybrid adaptive architectures. It reviews evaluation resources, emphasizing the need to assess graph access, evidence retrieval, updating, provenance, uncertainty, memory stability, and computational cost separately. Particular attention is given to graph-based agent memory, where KGs support persistent knowledge, world modeling, inference, tool and agent coordination, and governance of shared assertions. A running example of a scientific literature analyst illustrates these capabilities and their operational requirements. The chapter identifies key challenges in graph versioning, runtime logical validation, executable graph access, source discovery, and metadata interoperability. It outlines three future directions: data search engines combining natural-language interaction with federated querying over the decentralized Web of Data, a common semantic layer connecting diverse knowledge organization systems, and generative models that operate directly on language-independent semantic representations. It argues that the value of integration depends on task requirements and on maintaining graph memory that is accurate, auditable, reversible, and governable over time.
KW - Knowledge graphs
KW - Large language models
KW - Neuro-symbolic AI
KW - Agentic AI
KW - Graph-based agent memory
KW - GraphRAG
KW - Semantic Web
KW - Federated querying
KW - Knowledge provenance
KW - Knowledge management
KW - Wissensgraphen
KW - Große Sprachmodelle
KW - Neuro-symbolische KI
KW - Agentische KI
KW - Graphbasiertes Agentengedächtnis
KW - GraphRAG
KW - Semantisches Web
KW - Föderierte Abfragen
KW - Wissensprovenienz
KW - Wissensmanagement
M3 - Chapter in edited volume
SN - 9780443452444
T3 - Intelligent Data-Centric Systems
SP - 185
EP - 212
BT - Knowledge Graphs and Large Language Models
A2 - Tiwari, Sanju
A2 - Groppe, Sven
A2 - Groppe, Jinghua
A2 - Mihindukulasooriya, Nandana
PB - Academic Press
CY - London/Cambridge, MA
ER -