LLMs for Graph Learning

This field studies how large language models can learn from and reason about graphs, including text-attributed networks, knowledge graphs, molecules, and evolving graphs. Common tasks include node and link prediction, graph classification, anomaly detection, knowledge graph completion, and graph question answering. Approaches serialize graph neighborhoods as text, add graph-aware tokens or attention, combine LLMs with graph neural networks, or use prompting, fine-tuning, distillation, and agents to guide graph exploration. Models can benefit from rich textual knowledge and scarce labels, but benchmarks and analyses show that they may fail to use topology reliably, especially on large or exact graph tasks; balancing semantic reasoning, structural fidelity, and efficient inference remains an open challenge.