Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information. Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system. Building on this foundation, graph-based RAG systems go a step further by retrieving subgraphs, which preserve the relationships between knowledge entities and provide more comprehensive context. However, graph RAG faces two challenges: (1) Retrieving relevant information introduces irrelevant nodes (especially in dense graph databases, where retrieval usually extends to adjacent nodes), and leads to overly lengthy inputs that hinder efficiency; (2) The representation gap between graph and language during generation with LLMs limits the ability to fully leverage graph structures for enhanced understanding. To address these limitations, we propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase. It first formulates a subgraph by retrieving nodes and edges. Then an Aligner is proposed to jointly optimizes a graph encoder with LLM-summarized reasoning. It achieves dual alignment of graph node and representation by leveraging KL divergence loss and contrastive loss, facilitating efficient pruning of irrelevant knowledge and establishing a unified semantic space. The Generator integrates the aligned graph data with LLM to produce coherent and accurate answers. Experiments on GraphQA benchmark across three tasks (including common sense reasoning, scene graph understanding, and knowledge graph reasoning) validate the effectiveness of our method. The code will be available upon accepted.
View on arXiv@article{xu2025_2505.16237,
title={ Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation },
author={ Derong Xu and Pengyue Jia and Xiaopeng Li and Yingyi Zhang and Maolin Wang and Qidong Liu and Xiangyu Zhao and Yichao Wang and Huifeng Guo and Ruiming Tang and Enhong Chen and Tong Xu },
journal={arXiv preprint arXiv:2505.16237},
year={ 2025 }
}