Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Derong, Jia, Pengyue, Li, Xiaopeng, Zhang, Yingyi, Wang, Maolin, Liu, Qidong, Zhao, Xiangyu, Wang, Yichao, Guo, Huifeng, Tang, Ruiming, Chen, Enhong, Xu, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911370564337664
author Xu, Derong
Jia, Pengyue
Li, Xiaopeng
Zhang, Yingyi
Wang, Maolin
Liu, Qidong
Zhao, Xiangyu
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Chen, Enhong
Xu, Tong
author_facet Xu, Derong
Jia, Pengyue
Li, Xiaopeng
Zhang, Yingyi
Wang, Maolin
Liu, Qidong
Zhao, Xiangyu
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Chen, Enhong
Xu, Tong
contents Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph-based retrieval-augmented generation (GRAG) enriches LLMs with knowledge by retrieving graphs leveraging relational evidence, but it faces two challenges: structure-coupled irrelevant knowledge introduced by neighbor expansion and structure-reasoning discrepancy between graph embeddings and LLM semantics. We propose \ourmodel, an anchor-and-rationale guided refinement framework to address these challenges. It prompts an LLM to extract anchors and rationale chains, which provide intermediate supervision for \textbf{(1) node-level alignment} that identifies critical nodes and prunes noisy evidence, and \textbf{(2) graph-level alignment} that bridges graph and language semantic spaces via contrastive learning. Extensive experiments on commonsense reasoning, scene graph understanding, and knowledge graph reasoning demonstrate consistent gains over 18 strong baselines, validating the effectiveness of \ourmodel for improving graph-grounded generation. The code can be found in https://anonymous.4open.science/r/Align-GRAG-F3D8/.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
Xu, Derong
Jia, Pengyue
Li, Xiaopeng
Zhang, Yingyi
Wang, Maolin
Liu, Qidong
Zhao, Xiangyu
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Chen, Enhong
Xu, Tong
Computation and Language
Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph-based retrieval-augmented generation (GRAG) enriches LLMs with knowledge by retrieving graphs leveraging relational evidence, but it faces two challenges: structure-coupled irrelevant knowledge introduced by neighbor expansion and structure-reasoning discrepancy between graph embeddings and LLM semantics. We propose \ourmodel, an anchor-and-rationale guided refinement framework to address these challenges. It prompts an LLM to extract anchors and rationale chains, which provide intermediate supervision for \textbf{(1) node-level alignment} that identifies critical nodes and prunes noisy evidence, and \textbf{(2) graph-level alignment} that bridges graph and language semantic spaces via contrastive learning. Extensive experiments on commonsense reasoning, scene graph understanding, and knowledge graph reasoning demonstrate consistent gains over 18 strong baselines, validating the effectiveness of \ourmodel for improving graph-grounded generation. The code can be found in https://anonymous.4open.science/r/Align-GRAG-F3D8/.
title Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2505.16237