Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks.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/.

翻译：尽管大型语言模型（LLM）具备强大能力，但其仍存在幻觉问题且依赖过时知识，这在知识密集型任务中引发担忧。基于图的检索增强生成（GRAG）通过利用关系证据检索图结构知识来增强LLM，但面临两大挑战：邻域扩展引入的结构耦合无关知识，以及图嵌入与LLM语义间的结构推理差异。本文提出\ourmodel，一种基于锚点与推理链引导的优化框架以应对这些挑战。该框架提示LLM提取锚点及推理链，为以下两个过程提供中间监督：\textbf{（1）节点级对齐}——识别关键节点并剪枝噪声证据；\textbf{（2）图级对齐}——通过对比学习桥接图与语言语义空间。在常识推理、场景图理解与知识图谱推理任务上的大量实验表明，本方法在18个强基线模型上均取得稳定提升，验证了\ourmodel在改善图基生成任务中的有效性。代码公开于：https://anonymous.4open.science/r/Align-GRAG-F3D8/。