Prompt Engineering With Enterprise Information for LLMs and GenAI
source link: https://www.gartner.com/en/documents/4520799
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Published: 12 July 2023
Summary
Training and fine-tuning custom large language models for generative artificial intelligence is beyond the capabilities of most organizations. Technical professionals can use prompt engineering and in-context learning to meet the needs of most generative AI scenarios.
Included in Full Research
Key Findings
Training and fine-tuning custom large language models (LLMs) is impractical for most organizations. The technical and computational requirements call for very mature data management practices and significant data science expertise.
Most enterprise use cases can be accomplished with a combination of prompt engineering and in-context learning to ground LLM responses in enterprise information and constraints. Several approaches to prompt creation are available to support generative AI (GenAI) applications.
Retrieval augmented generation is a practical approach to prompt engineering that incorporates private and proprietary enterprise information into GenAI applications without requiring the underlying model to be modified in any way.
Recommendations
Technical professionals
Clients can log in to view the entire document.
Analysts:
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK