Knowledge Base Question Generation (KBQG) aims to generate human-readable questions from a collection of factual triples and a given answer entity. Approaches that utilize pre-trained language models improve question generation performance, yet they are still limited by the inherent limitations of these models. In contrast, Large Language Models (LLMs) possess more advanced capabilities in language understanding and generation. However, directly applying LLMs often results in questions that do not correspond well to the target answers or the structure of the subgraph. To address this issue, we devise DERA, a Dual-Encoder Retrieval-Augmented framework that guides LLMs using structurally similar subgraph examples as enhanced prompts. DERA identifies similar subgraphs through a dual encoder that captures structural features from multiple perspectives and applies contrastive learning to optimize the representations. Experiments on the WebQuestions and PathQuestions datasets show that DERA achieves consistent improvements across multiple evaluation metrics and shows strong cross-domain adaptability.

Knowledge graph-to-text (KG-to-text) generation involves generating fluent and faithful text from structured data within knowledge graphs. Existing methods typically linearize the graph data and use pre-trained models, but they often neglect the complexity of graph structures and relations, limiting their ability to capture information effectively. In this paper, we propose a hierarchical attention model named ESSI-KG, which utilizes positional embeddings and attention mechanisms to enhance the representation and learning of relational information within knowledge graphs. We design three types of positional visualization embedding layers to encode graph structure information into sequences, thereby more effectively capturing the local information within triples in the knowledge graph. Additionally, we introduce entity attention layers and relation attention layers to retain global graph structure information and focus on relations among triples in the knowledge graph. Extensive experiments conducted on four benchmark datasets provide compelling evidence that ESSI-KG outperforms existing state-of-the-art models, demonstrating enhanced logical consistency and producing more accurate and informative textual outputs. Our model attains a BLEU-4 score that exceeds other baselines by over 1.27 on WebNLG. Specifically, under the few-shot settings, ESSI-KG reaches baseline performance with only one-twentieth of the labeled examples typically required.