Large Language Models as Sous Chefs: Revising Recipes with GPT-3
This work addresses the challenge of improving usability of written instructions like recipes for general users, though it is incremental as it applies existing LLM capabilities to a new domain.
The authors tackled the problem of making complex recipes easier to use by developing a prompt for large language models to revise them into simpler steps, finding that human annotators usually preferred the revisions over the originals.
With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and understand. In our work, we focus on recipes as an example of complex, diverse, and widely used instructions. We develop a prompt grounded in the original recipe and ingredients list that breaks recipes down into simpler steps. We apply this prompt to recipes from various world cuisines, and experiment with several large language models (LLMs), finding best results with GPT-3.5. We also contribute an Amazon Mechanical Turk task that is carefully designed to reduce fatigue while collecting human judgment of the quality of recipe revisions. We find that annotators usually prefer the revision over the original, demonstrating a promising application of LLMs in serving as digital sous chefs for recipes and beyond. We release our prompt, code, and MTurk template for public use.