This repository curates research papers and resources on unifying Large Language Models (LLMs) and Knowledge Graphs (KGs). It addresses the limitations of LLMs in factual knowledge recall and KGs in construction and dynamic updates by exploring synergistic frameworks. The target audience includes researchers and practitioners in NLP, AI, and knowledge representation seeking to leverage the strengths of both LLMs and KGs.

How It Works

The project categorizes advancements into three primary frameworks: KG-enhanced LLMs, LLMs-augmented KGs, and Synergized LLMs + KGs. This structured approach provides a roadmap for understanding the landscape, detailing techniques and applications within each category, and facilitating research in this emerging interdisciplinary field.

Quick Start & Requirements

This repository is a curated list of papers and does not have a direct installation or execution command. It serves as a reference guide.

Highlighted Details

• Comprehensive roadmap paper published in IEEE Transactions on Knowledge and Data Engineering (TKDE).
• Collection includes papers on KG-enhanced LLM pre-training, inference, and interpretability.
• Features research on LLM-augmented KG embedding, completion, and question answering.
• Covers synergistic approaches for knowledge representation, reasoning, and applications like recommendation and fault analysis.

Maintenance & Community

The project is under active development, with recent news highlighting accepted papers at major conferences like NeurIPS, ACL, and ICLR. The primary contributors are RManLuo and associated researchers.

Licensing & Compatibility

The repository itself is not licensed for software distribution. Individual papers retain their original publication licenses. Compatibility for commercial use or closed-source linking depends on the licenses of the cited research papers and their associated codebases.

Limitations & Caveats

This is a curated list of research papers and not a runnable software project. Users must refer to individual papers for implementation details, code availability, and specific technical requirements. The project's "under development" status implies ongoing curation and potential for new content.