Paper Type
Complete
Abstract
As generative AI (GenAI) adoption accelerates, industries face the challenge of integrating these technologies into their workflows. This study addresses the gap in prompt engineering frameworks needed to enhance LLM accuracy in industrial applications. We investigate a multifaceted approach incorporating contextual cues, directive language, and structured outputs, drawing on human communication paradigms. Our research study introduces prompt tuning and chain-of-thought prompting to reduce user input and clarify AI decision-making. Our study findings indicate that these methods can streamline complex processes, such as employee onboarding, paving the way for wider GenAI adoption. The study advocates for customizing GenAI to specific industrial tasks and calls for increased model transparency to bridge data gaps and mitigate "black box" issues. The contribution demonstrates prompt engineering's role in improving operational efficiency and precision, promoting GenAI's broader implementation in business settings.
Paper Number
1716
Recommended Citation
Micus, Christian; Dekova, Ani; Böttcher, Timo Phillip; and Krcmar, Helmut, "Chat Your Data: Prompt Engineering for Standardized GenAI Results" (2024). AMCIS 2024 Proceedings. 7.
https://aisel.aisnet.org/amcis2024/fow/fow/7
Chat Your Data: Prompt Engineering for Standardized GenAI Results
As generative AI (GenAI) adoption accelerates, industries face the challenge of integrating these technologies into their workflows. This study addresses the gap in prompt engineering frameworks needed to enhance LLM accuracy in industrial applications. We investigate a multifaceted approach incorporating contextual cues, directive language, and structured outputs, drawing on human communication paradigms. Our research study introduces prompt tuning and chain-of-thought prompting to reduce user input and clarify AI decision-making. Our study findings indicate that these methods can streamline complex processes, such as employee onboarding, paving the way for wider GenAI adoption. The study advocates for customizing GenAI to specific industrial tasks and calls for increased model transparency to bridge data gaps and mitigate "black box" issues. The contribution demonstrates prompt engineering's role in improving operational efficiency and precision, promoting GenAI's broader implementation in business settings.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
FOW