Introducing ChatSQC: enhancing statistical quality control with augmented AI
Publication date
2024-10-10
Document type
Forschungsartikel
Author
Megahed, Fadel M.
Chen, Ying-Ju
Zwetsloot, Inez M.
Montgomery, Douglas C.
Jones-Farmer, L. Allison
Organisational unit
Scopus ID
Publisher
Taylor & Francis
Series or journal
Journal of Quality Technology
ISSN
Periodical volume
56
Periodical issue
5
First page
474
Last page
497
Part of the university bibliography
✅
Language
English
Keyword
artificial intelligence
ChatGPT
generative AI
langchain
large language models (LLM)
quality control
statistical process monitoring
Abstract
We introduce ChatSQC, an innovative chatbot system that combines the power of OpenAI’s Large Language Models (LLM) with a specific knowledge base in Statistical Quality Control (SQC). Our research focuses on enhancing LLMs using specific SQC references, shedding light on how data preprocessing parameters and LLM selection impact the quality of generated responses. By illustrating this process, we hope to motivate wider community engagement to refine LLM design and output appraisal techniques. We also highlight potential research opportunities within the SQC domain that can be facilitated by leveraging ChatSQC, thereby broadening the application spectrum of SQC. A primary goal of our work is to provide a template and proof-of-concept on how LLMs can be utilized by our community. To continuously improve ChatSQC, we ask the SQC community to provide feedback, highlight potential issues, request additional features, and/or contribute via pull requests through our public GitHub repository. Additionally, the team will continue to explore adding supplementary reference material that would further improve the contextual understanding of the chatbot. Overall, ChatSQC serves as a testament to the transformative potential of AI within SQC, and we hope it will spur further advancements in the integration of AI in this field.
Version
Published version
Access right on openHSU
Metadata only access