Saved in:
Bibliographic Details
Main Authors: Luo, Zhongze, Wan, Weixuan, Zhang, Tianya, Wang, Dan, Tang, Xiaoying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.07037
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908593163337728
author Luo, Zhongze
Wan, Weixuan
Zhang, Tianya
Wang, Dan
Tang, Xiaoying
author_facet Luo, Zhongze
Wan, Weixuan
Zhang, Tianya
Wang, Dan
Tang, Xiaoying
contents The rapid evolution of communication technologies has led to an explosion of standards, rendering traditional expert-dependent consultation methods inefficient and slow. To address this challenge, we propose \textbf{KG2QA}, a question answering (QA) framework for communication standards that integrates fine-tuned large language models (LLMs) with a domain-specific knowledge graph (KG) via a retrieval-augmented generation (RAG) pipeline. We construct a high-quality dataset of 6,587 QA pairs from ITU-T recommendations and fine-tune Qwen2.5-7B-Instruct, achieving significant performance gains: BLEU-4 increases from 18.86 to 66.90, outperforming both the base model and Llama-3-8B-Instruct. A structured KG containing 13,906 entities and 13,524 relations is built using LLM-assisted triple extraction based on a custom ontology. In our KG-RAG pipeline, the fine-tuned LLMs first retrieves relevant knowledge from KG, enabling more accurate and factually grounded responses. Evaluated by DeepSeek-V3 as a judge, the KG-enhanced system improves performance across five dimensions, with an average score increase of 2.26\%, demonstrating superior factual accuracy and relevance. Integrated with Web platform and API, KG2QA delivers an efficient and interactive user experience. Our code and data have been open-sourced https://github.com/luozhongze/KG2QA.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KG2QA: Knowledge Graph-enhanced Retrieval-augmented Generation for Communication Standards Question Answering
Luo, Zhongze
Wan, Weixuan
Zhang, Tianya
Wang, Dan
Tang, Xiaoying
Computation and Language
The rapid evolution of communication technologies has led to an explosion of standards, rendering traditional expert-dependent consultation methods inefficient and slow. To address this challenge, we propose \textbf{KG2QA}, a question answering (QA) framework for communication standards that integrates fine-tuned large language models (LLMs) with a domain-specific knowledge graph (KG) via a retrieval-augmented generation (RAG) pipeline. We construct a high-quality dataset of 6,587 QA pairs from ITU-T recommendations and fine-tune Qwen2.5-7B-Instruct, achieving significant performance gains: BLEU-4 increases from 18.86 to 66.90, outperforming both the base model and Llama-3-8B-Instruct. A structured KG containing 13,906 entities and 13,524 relations is built using LLM-assisted triple extraction based on a custom ontology. In our KG-RAG pipeline, the fine-tuned LLMs first retrieves relevant knowledge from KG, enabling more accurate and factually grounded responses. Evaluated by DeepSeek-V3 as a judge, the KG-enhanced system improves performance across five dimensions, with an average score increase of 2.26\%, demonstrating superior factual accuracy and relevance. Integrated with Web platform and API, KG2QA delivers an efficient and interactive user experience. Our code and data have been open-sourced https://github.com/luozhongze/KG2QA.
title KG2QA: Knowledge Graph-enhanced Retrieval-augmented Generation for Communication Standards Question Answering
topic Computation and Language
url https://arxiv.org/abs/2506.07037