Towards Fine-Dining Recipe Generation with Generative Pre-trained Transformers

TL;DR

This paper explores using pre-trained Transformers to generate fine-dining recipes from limited data, focusing on recipe creation, technique identification, and minimal fine-tuning.

Contribution

It introduces a novel approach of applying auto-regressive language models to recipe generation with small datasets, emphasizing minimal fine-tuning.

Findings

Transformers can generate plausible recipes from limited data

Fine-tuning enhances recipe quality and diversity

Models identify cooking techniques effectively

Abstract

Food is essential to human survival. So much so that we have developed different recipes to suit our taste needs. In this work, we propose a novel way of creating new, fine-dining recipes from scratch using Transformers, specifically auto-regressive language models. Given a small dataset of food recipes, we try to train models to identify cooking techniques, propose novel recipes, and test the power of fine-tuning with minimal data.