TY - JOUR
AU - Jun Xu
AU - Hao Zhang
AU - Haijing Zhang
AU - Jiawei Lu
AU - Gang Xiao
AB - Large language models are rapidly advancing the field of artificial intelligence, with current research focusing primarily on traditional natural language understanding tasks, such as question answering and information extraction. However, in knowledge-intensive domains, such as intangible cultural heritage, hallucination problems due to insufficient domain knowledge persist. To address this, we present ChatTf, a knowledge graph-enhanced intelligent Q\&A system, exemplified by Chinese traditional folklore, aimed at reducing factuality hallucinations in this domain. Specifically, we constructed the Traditional Folklore Ontology (TFOnto) and proposed the Zero-shot Traditional Folklore Triplet Extraction (ZFTE) framework. Driven by TFOnto, ZFTE builds a Traditional Folklore Knowledge Graph (TFKG). We then proposed a dual-stage Retrieval-Augmented Generation framework (TFKG-RAG) based on TFKG to provide traditional folklore knowledge to large language models, mitigating factuality hallucinations in folklore Q\&A tasks. In the experimental phase, ChatTf achieved an accuracy of 96.7\% on a self-built TFCQD test set, outperforming several state-of-the-art baseline methods. This demonstrates the accuracy and reliability of folklore domain question answering.
BT - IEEE Access
DO - 10.1109/ACCESS.2024.3485877
N2 - Large language models are rapidly advancing the field of artificial intelligence, with current research focusing primarily on traditional natural language understanding tasks, such as question answering and information extraction. However, in knowledge-intensive domains, such as intangible cultural heritage, hallucination problems due to insufficient domain knowledge persist. To address this, we present ChatTf, a knowledge graph-enhanced intelligent Q\&A system, exemplified by Chinese traditional folklore, aimed at reducing factuality hallucinations in this domain. Specifically, we constructed the Traditional Folklore Ontology (TFOnto) and proposed the Zero-shot Traditional Folklore Triplet Extraction (ZFTE) framework. Driven by TFOnto, ZFTE builds a Traditional Folklore Knowledge Graph (TFKG). We then proposed a dual-stage Retrieval-Augmented Generation framework (TFKG-RAG) based on TFKG to provide traditional folklore knowledge to large language models, mitigating factuality hallucinations in folklore Q\&A tasks. In the experimental phase, ChatTf achieved an accuracy of 96.7\% on a self-built TFCQD test set, outperforming several state-of-the-art baseline methods. This demonstrates the accuracy and reliability of folklore domain question answering.
PY - 2024
SP - 162638
EP - 162650
T2 - IEEE Access
TI - ChatTf: A Knowledge Graph-Enhanced Intelligent Q\&A System for Mitigating Factuality Hallucinations in Traditional Folklore
VL - 12
SN - 2169-3536
ER -