Position: How can Graphs Help Large Language Models?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xiyuan, Hu, Yi, Wang, Yanbo, Shi, Chuan, Zhang, Muhan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917457847910400
author Wang, Xiyuan
Hu, Yi
Wang, Yanbo
Shi, Chuan
Zhang, Muhan
author_facet Wang, Xiyuan
Hu, Yi
Wang, Yanbo
Shi, Chuan
Zhang, Muhan
contents With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompting techniques-such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)-enhance LLM reasoning capabilities, and 3) integrating graphs into LLMs improves their understanding of structured data, expanding their applicability to domains such as e-commerce, code, and relational databases (RDBs). We further outlook some future directions including designing sparse LLM architectures based on graphs and brain-inspired memory systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02452
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Position: How can Graphs Help Large Language Models?
Wang, Xiyuan
Hu, Yi
Wang, Yanbo
Shi, Chuan
Zhang, Muhan
Artificial Intelligence
With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompting techniques-such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)-enhance LLM reasoning capabilities, and 3) integrating graphs into LLMs improves their understanding of structured data, expanding their applicability to domains such as e-commerce, code, and relational databases (RDBs). We further outlook some future directions including designing sparse LLM architectures based on graphs and brain-inspired memory systems.
title Position: How can Graphs Help Large Language Models?
topic Artificial Intelligence
url https://arxiv.org/abs/2605.02452