Enhancing Retrieval-Augmented Generation with Knowledge Graph-Based Soft-Labeling and Triplet Similarity SBERT
學年 113
學期 2
發表日期 2025-07-16
作品名稱 Enhancing Retrieval-Augmented Generation with Knowledge Graph-Based Soft-Labeling and Triplet Similarity SBERT
作品名稱（其他語言）
著者 Yu-Ting Yang; Jia-Yang Jiang; Yi-Ti Lin; Chih-Yung Chang
作品所屬單位
出版者
會議名稱 IEEE ICCE-TW 2025
會議地點 Kaohsiung, Taiwan
摘要 In recent years, generative AI has made significant progress in natural language generation, including applications in customer service. Retrieval-Augmented Generation (RAG) technology has been widely used to enhance the accuracy and relevance of AI-generated responses by integrating external knowledge retrieval. This paper proposes an improved RAG system that employs knowledge graphs and a triplet similarity SBERT framework to refine text retrieval performance. The proposed model introduces soft-label generation for training, optimizing textual representation learning and retrieval quality. Experimental results demonstrate that our method outperforms existing retrieval models in accuracy and efficiency.
關鍵字
語言 en
收錄於
會議性質 國際
校內研討會地點 無
研討會時間 20250716~20250718
通訊作者
國別 USA
公開徵稿
出版型式
出處
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/128903 )

SDGS 尊嚴就業與經濟發展,產業創新與基礎設施