KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bui, Chi Minh, Thieu, Ngoc Mai, Nguyen, Van Vinh, Jung, Jason J., Bui, Khac-Hoai Nam
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908521913647104
author Bui, Chi Minh
Thieu, Ngoc Mai
Nguyen, Van Vinh
Jung, Jason J.
Bui, Khac-Hoai Nam
author_facet Bui, Chi Minh
Thieu, Ngoc Mai
Nguyen, Van Vinh
Jung, Jason J.
Bui, Khac-Hoai Nam
contents The integration of knowledge graphs (KGs) with large language models (LLMs) offers significant potential to improve the retrieval phase of 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 the contextual representation of complex input queries using 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 RAGBench and MultiHop-RAG datasets demonstrate KG-CQR's superior performance, achieving a 4-6% improvement in mAP and a 2-3% improvement in Recall@25 over strong baseline models. Furthermore, evaluations on challenging RAG tasks such as multi-hop question answering show that, by incorporating KG-CQR, the performance consistently outperforms the existing baseline in terms of retrieval effectiveness
format Preprint
id arxiv_https___arxiv_org_abs_2508_20417
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
Bui, Chi Minh
Thieu, Ngoc Mai
Nguyen, Van Vinh
Jung, Jason J.
Bui, Khac-Hoai Nam
Computation and Language
Databases
The integration of knowledge graphs (KGs) with large language models (LLMs) offers significant potential to improve the retrieval phase of 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 the contextual representation of complex input queries using 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 RAGBench and MultiHop-RAG datasets demonstrate KG-CQR's superior performance, achieving a 4-6% improvement in mAP and a 2-3% improvement in Recall@25 over strong baseline models. Furthermore, evaluations on challenging RAG tasks such as multi-hop question answering show that, by incorporating KG-CQR, the performance consistently outperforms the existing baseline in terms of retrieval effectiveness
title KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval
topic Computation and Language
Databases
url https://arxiv.org/abs/2508.20417