Prompt Patterns For PDS4 Information Modeling

Prompt Patterns provide general and reusable solutions to commonly occurring problems within specific contexts while interacting with a Large Language Model (LLM) such as GPT4. A catalog of generic prompt engineering patterns [1] has been published to help users improve LLM results and to promote further research into prompt engineering. Software engineering software patterns are an analog to prompt patterns, providing reusable solutions to common problems in a particular context.

The catalog defines six categories of prompt patterns including Input Semantics, Output Customization, Error Identification, Prompt Improvement, Interaction, and Context Control. Prompt patterns from two of the categories, Input Semantics and Output Customization have been applied to problems found in information modeling for the Planetary Data System (PDS).