Journal article
LogiCode: An LLM-Driven Framework for Logical Anomaly Detection
Abstract
This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond the traditional focus on structural inconsistencies. By harnessing LLMs for logical reasoning, LogiCode autonomously generates Python codes to pinpoint anomalies such as incorrect component quantities or missing elements, marking a significant leap forward in anomaly detection …
Authors
Zhang Y; Cao Y; Xu X; Shen W
Journal
IEEE Transactions on Automation Science and Engineering, Vol. 22, , pp. 7712–7723
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Publication Date
January 1, 2025
DOI
10.1109/tase.2024.3468464
ISSN
1545-5955