The integration of knowledge graphs (KGs) with large language models (LLMs) offers significant potential to enhance the retrieval stage in retrieval-augmented generation (RAG) systems. In this study, we propose KG-CQR, a novel framework for Contextual Query Retrieval (CQR) that enhances the retrieval phase by enriching complex input queries with contextual representations derived from a corpus-centric KG. Unlike existing methods that primarily address corpus-level context loss, KG-CQR focuses on query enrichment through structured relation representations, extracting and completing relevant KG subgraphs to generate semantically rich query contexts. Comprising subgraph extraction, completion, and contextual generation modules, KG-CQR operates as a model-agnostic pipeline, ensuring scalability across LLMs of varying sizes without additional training. Experimental results on the RAGBench and MultiHop-RAG datasets demonstrate that KG-CQR outperforms strong baselines, achieving improvements of up to 4–6% in mAP and approximately 2–3% in Recall@25. Furthermore, evaluations on challenging RAG tasks such as multi-hop question answering show that, by incorporating KG-CQR, the performance outperforms the existing baseline in terms of retrieval effectiveness.

This study introduces Simple Reasoning with Code (SiRC), a novel instruction fine-tuning method for solving mathematical reasoning problems, particularly effective for Vietnamese, which is considered a low-resource language. Specifically, solving mathematical problems requires strategic and logical reasoning, which remains challenging in this research area. This paper presents a simple yet effective instruction fine-tuning method for mathematical reasoning. Unlike previous approaches, our proposed method effectively combines chain-of-thought reasoning with code transfer methods without requiring a sophisticated inference procedure. Furthermore, we focus on exploiting small open-source large language models (LLMs) for the Vietnamese language. In this regard, we first introduce a trainable Vietnamese math reasoning dataset, which is named ViMath-InstructCode. The proposed dataset is then used for fine-tuning open-source LLMs (e.g., less than 10 billion parameters). Experiments conducted on our custom ViMath-Bench dataset, the largest benchmarking dataset focusing on Vietnamese mathematical problems, indicate the promising results of our proposed method. Our source code and dataset are available for further exploitation.

The multilingual parallel corpus is an important resource for many applications of natural language processing (NLP). For machine translation, the size and quality of the training corpus mainly affects the quality of the translation models. In this work, we present the method for building high-quality multilingual parallel corpus in the news domain and for some low-resource languages, including Vietnamese, Laos, and Khmer, to improve the quality of multilingual machine translation in these areas. We also publicized this one that includes 500.000 Vietnamese-Chinese bilingual sentence pairs; 150.000 Vietnamese-Laos bilingual sentence pairs, and 150.000 Vietnamese-Khmer bilingual sentence pairs.