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 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 reason-and-construct paradigm and propose Relink, a framework that dynamically builds a query-specific evidence graph. To tackle incompleteness, 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.

Knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples. In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge. Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where itachieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors. The code is publicly available at https://github.com/HFUT-DMiC-Lab/TCR-QF.git.

Relation Extraction (RE) is a core task in Information Extraction that identifies relationships between entities in the text. Existing prompt construction methods using Large Language Models (LLMs) achieve success by providing demonstrations to enhance relation extraction abilities. However, these methods provide retrieved demonstrations that have weak relational correlations with the test input and overlook the importance of associated entities and label semantics in RE tasks. This results in incomplete prompt construction, leading to suboptimal alignment between LLMs and RE tasks. To address these issues, we propose a Relation-Aware Retrieval Augmented Generation model (RelAwareRAG) for relation extraction. Firstly, we design a relation-aware retrieval that can identify demonstrations more effectively aligned with the target entity relation by fine-tuning a pre-trained language model for the target RE task and generating task-specific representations. Secondly, we refine the candidate relation space through entity constraint pruning and perform label semantic projection for LLMs to optimize the prompt construction, thereby improving the adaptability of LLMs in relation extraction tasks. Extensive experiments on TACRED and TACREV show that RelAwareRAG achieves superior performance, with a 3.65% increase in F1 score on TACRED and a 3.76% improvement on TACREV.

The superior performance of large-scale pre-trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-tuning or transfer learning in subsequent tasks. After pre-training is complete, a small amount of labeled data can be used to fine-tune the model for a specific task or domain. This two-stage method of “pre-training+fine-tuning” has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-tuning patterns for specific NLP tasks than typical fixed fine-tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-training language models show the effectiveness and generality of the proposed framework.