Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Guangxin, Wang, Hanchen, Wang, Jianwei, Zhang, Wenjie, Zhang, Ying, Pei, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918169318260736
author Su, Guangxin
Wang, Hanchen
Wang, Jianwei
Zhang, Wenjie
Zhang, Ying
Pei, Jian
author_facet Su, Guangxin
Wang, Hanchen
Wang, Jianwei
Zhang, Wenjie
Zhang, Ying
Pei, Jian
contents Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining LLMs and TAGs yields complementary benefits: enhancing TAG representation learning and improving the reasoning and interpretability of LLMs. This survey provides the first systematic review of LLM--TAG integration from an orchestration perspective. We introduce a novel taxonomy covering two fundamental directions: LLM for TAG, where LLMs enrich graph-based tasks, and TAG for LLM, where structured graphs improve LLM reasoning. We categorize orchestration strategies into sequential, parallel, and multi-module frameworks, and discuss advances in TAG-specific pretraining, prompting, and parameter-efficient fine-tuning. Beyond methodology, we summarize empirical insights, curate available datasets, and highlight diverse applications across recommendation systems, biomedical analysis, and knowledge-intensive question answering. Finally, we outline open challenges and promising research directions, aiming to guide future work at the intersection of language and graph learning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21131
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
Su, Guangxin
Wang, Hanchen
Wang, Jianwei
Zhang, Wenjie
Zhang, Ying
Pei, Jian
Computation and Language
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining LLMs and TAGs yields complementary benefits: enhancing TAG representation learning and improving the reasoning and interpretability of LLMs. This survey provides the first systematic review of LLM--TAG integration from an orchestration perspective. We introduce a novel taxonomy covering two fundamental directions: LLM for TAG, where LLMs enrich graph-based tasks, and TAG for LLM, where structured graphs improve LLM reasoning. We categorize orchestration strategies into sequential, parallel, and multi-module frameworks, and discuss advances in TAG-specific pretraining, prompting, and parameter-efficient fine-tuning. Beyond methodology, we summarize empirical insights, curate available datasets, and highlight diverse applications across recommendation systems, biomedical analysis, and knowledge-intensive question answering. Finally, we outline open challenges and promising research directions, aiming to guide future work at the intersection of language and graph learning.
title Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.21131