Unifying Large Language Models and Knowledge Graphs: A Roadmap

🤖 Plain-English Summary

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. Our roadmap consists of three general frameworks, namely, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1) KG-enhanced LLMs,</i> which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understan...

🔑 Key Findings

• 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.

🔗 Related Resources