Unifying Large Language Models and Knowledge Graphs: A Roadmap
Объединение больших языковых моделей и графов знаний: дорожная карта
2024-01-10
SCID: 54.1/dwg2nwsx
Discuss with AI
KG-enhanced LLMsLLM-augmented KGsbidirectional reasoningknowledge graphslarge language models
Figures from the paper
Abstract (AI)
Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolve by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely,1) KG-enhanced LLMs,which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs;2) LLM-augmented KGs,that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering; and3) Synergized LLMs + KGs, in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions.
Key Findings
1
A mutually beneficial LLM–KG integration is proposed as a basis for bidirectional reasoning driven jointly by data and structured knowledge, with future research directions identified.
2
Knowledge graphs offer structured, explicit factual knowledge that can improve LLM inference and interpretability, but are difficult to construct and continuously evolve.
3
LLMs can support KG embedding, completion, construction, graph-to-text generation, and question answering, addressing challenges in generating and representing new knowledge.
4
Large language models provide strong generalization but remain black-box systems that often struggle to capture and access factual knowledge.
5
The paper organizes LLM–KG integration into three frameworks: KG-enhanced LLMs, LLM-augmented KGs, and synergized LLMs plus KGs.
Research Object
the unification of large language models (LLMs) and knowledge graphs (KGs)
Research Subject
frameworks, methods, and future research directions for mutually leveraging LLMs and KGs to improve factual knowledge access, interpretability, knowledge construction, completion, and bidirectional reasoning
Publication Details
Publication Date
2024-01-10
Journal
Publisher
ISSN
Cited by
2567
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai16
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer2019
LLaMA: Open and Efficient Foundation Language Models2023
A Survey of Large Language Models2026
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks2020
Training language models to follow instructions with human feedback2022
Learning Entity and Relation Embeddings for Knowledge Graph Completion2015
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge2017
Longformer: The Long-Document Transformer2020
🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models2025
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey2023
REALM: Retrieval-Augmented Language Model Pre-Training2020
K-BERT: Enabling Language Representation with Knowledge Graph2020
AgentTuning: Enabling Generalized Agent Abilities for LLMs2024
Qualitative Spatial Reasoning over Questions (Short Paper)2022
Cited by11
A Survey on Evaluation of Large Language Models2024
Large Language Models for Software Engineering: A Systematic Literature Review2024
Software Testing With Large Language Models: Survey, Landscape, and Vision2024
Large Language Models for Cyber Security: A Systematic Literature Review2025
Graph Retrieval-Augmented Generation: A Survey2025
Combating misinformation in the age of LLMs: Opportunities and challenges2024
Construction of Knowledge Graphs: Current State and Challenges2024
Large Language Models and Knowledge Graphs: Opportunities and Challenges2023
Knowledge Graphs and Their Reciprocal Relationship with Large Language Models2025
From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications2026
Graphusion: A RAG Framework for Scientific Knowledge Graph Construction with a Global Perspective2025