SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graph

Knowledge graphs (KGs) play a pivotal role in knowledge-intensive tasks across specialized domains, where the acquisition of precise and dependable knowledge is crucial. However, existing KG construction methods heavily rely on human intervention to attain qualified KGs, which severely hinders the practical applicability in real-world scenarios. To address this challenge, we propose a general KG construction framework, named SAC-KG, to exploit large language models (LLMs) as Skilled Automatic Constructors for domain Knowledge Graph. SAC-KG effectively involves LLMs as domain experts to generate specialized and precise multi-level KGs. Specifically, SAC-KG consists of three components: Generator, Verifier, and Pruner. For a given entity, Generator produces its relations and tails from raw domain corpora, to construct a specialized single-level KG. Verifier and Pruner then work together to ensure precision by correcting generation errors and determining whether newly produced tails require further iteration for the next-level KG. Experiments demonstrate that SAC-KG automatically constructs a domain KG at the scale of over one million nodes and achieves a precision of 89.32%, leading to a superior performance with over 20% increase in precision rate compared to existing state-of-the-art methods for the KG construction task. * Corresponding author. This work was done when Hanzhu Chen was an intern at Alibaba Cloud. GPT-KG all correct Correct (a) All correct triples extracted from the full version of SAC-KG. GPT-KG Correct Error (b) Triples generated by the full version of SAC-KG. GPT-KG w/o prompt Correct Error (c) Triples generated by SAC-KG w/o prompt . GPT-KG w/o text Correct Error (d) Triples generated by SAC-KG w/o text . GPT-KG w/o verifier Correct Error (e) Triples generated by SAC-KG w/o verif ier . (f) Triples generated by SAC-KG w/o pruner . Correct triples Wrong triples commonly called rice black-streaked dwarf disease c modes of transmission c distribution area (a) Rice disease case study for SAC-KG.