Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG methods are constrained by a prevailing \textit{build-then-reason} paradigm, which relies on a static, pre-constructed Knowledge Graph (KG). This paradigm faces two critical challenges. First, the KG's inherent incompleteness often breaks reasoning paths. Second, the graph's low signal-to-noise ratio introduces distractor facts, presenting query-relevant but misleading knowledge that disrupts the reasoning process. To address these challenges, we argue for a \textit{reason-and-construct} paradigm and propose Relink, a framework that dynamically builds a query-specific evidence graph. To tackle incompleteness, \textbf{Relink} instantiates required facts from a latent relation pool derived from the original text corpus, repairing broken paths on the fly. To handle misleading or distractor facts, Relink employs a unified, query-aware evaluation strategy that jointly considers candidates from both the KG and latent relations, selecting those most useful for answering the query rather than relying on their pre-existence. This empowers Relink to actively discard distractor facts and construct the most faithful and precise evidence path for each query. Extensive experiments on five Open-Domain Question Answering benchmarks show that Relink achieves significant average improvements of 5.4\% in EM and 5.2\% in F1 over leading GraphRAG baselines, demonstrating the superiority of our proposed framework.

翻译：基于图的检索增强生成（GraphRAG）通过将大语言模型（LLM）建立在结构化知识基础上，有效缓解了其幻觉问题。然而，当前GraphRAG方法受限于主流的“先构建后推理”范式，该范式依赖于静态预构建的知识图谱（KG）。此范式面临两个关键挑战：首先，知识图谱固有的不完整性常导致推理路径中断；其次，图谱的低信噪比会引入干扰性事实，这些与查询相关但具有误导性的知识会扰乱推理过程。为应对这些挑战，我们提出“推理即构建”范式，并设计Relink框架以动态构建面向特定查询的证据图。针对不完整性问题，Relink从原始文本语料衍生的潜在关系池中实例化所需事实，实时修复断裂路径。针对误导性或干扰性事实，Relink采用统一的查询感知评估策略，联合考量来自知识图谱和潜在关系的候选事实，选择对回答查询最有用的信息而非依赖其预存状态。这使得Relink能够主动剔除干扰性事实，为每个查询构建最忠实且精确的证据路径。在五个开放域问答基准上的大量实验表明，Relink相较于主流GraphRAG基线模型，在EM和F1指标上分别实现了5.4%和5.2%的平均显著提升，验证了所提框架的优越性。