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

TL;DR

Align-GRAG introduces an anchor-and-rationale guided framework that enhances graph retrieval-augmented generation by improving node and graph alignment, leading to better knowledge grounding in LLMs for reasoning tasks.

Contribution

It proposes a novel anchor-and-rationale guided refinement framework that addresses structure-related challenges in graph-grounded LLM generation, improving alignment and knowledge relevance.

Findings

Consistent performance improvements over 18 baselines.

Effective node-level pruning of noisy evidence.

Enhanced graph-semantic space bridging via contrastive learning.

Abstract

Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks.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