Can I read Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency on EtoBox?

Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency by Choubey, Prafulla Kumar; Su, Xin; Luo, Man; Peng, Xiangyu; Xiong, Caiming; Le, Tiep; Rosenman, Shachar; Lal, Vasudev; Mui, Phil; Ho, Ricky; Howard, Phillip; Wu, Chien-Sheng is a scholarly article available to read on EtoBox.

What is Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency about?

Knowledge graphs (KGs) generated by large language models (LLMs) are becoming increasingly valuable for Retrieval-Augmented Generation (RAG) applications that require knowledge-intensive reasoning. However, existing KG extraction methods predominantly rely on prompt-based approaches, which are inefficient for processing large-scale corpora. These approaches often suffer from information loss, particularly with long documents, due to the lack of specialized design for KG construction. Additionally, there is a gap in evaluation datasets and methodologies for ontology-free KG construction. To overcome these limitations, we propose SynthKG, a multi-step, document-level ontology-free KG synthesis workflow based on LLMs. By fine-tuning a smaller LLM on the synthesized document-KG pairs, we streamline the multi-step process into a single-step KG generation approach called Distill-SynthKG, substantially reducing the number of LLM inference calls. Furthermore, we re-purpose existing question-answering datasets to establish KG evaluation datasets and introduce new evaluation metrics. Using KGs produced by Distill-SynthKG, we also design a novel graph-based retrieval framework for RAG. Experi

Author

Choubey, Prafulla Kumar; Su, Xin; Luo, Man; Peng, Xiangyu; Xiong, Caiming; Le, Tiep; Rosenman, Shachar; Lal, Vasudev; Mui, Phil; Ho, Ricky; Howard, Phillip; Wu, Chien-Sheng

Published

2024

Language

EN