Monte Carlo Tree Search for Recipe Generation using GPT-2

TL;DR

This paper introduces RecipeMC, a novel recipe generation method combining GPT-2 with Monte Carlo Tree Search to produce more credible and preference-aligned culinary recipes, outperforming baseline models according to human evaluations.

Contribution

The paper presents a new text generation approach using MCTS with GPT-2, enabling soft constraints for more realistic and preferred recipe creation.

Findings

Human evaluators prefer RecipeMC-generated recipes over baselines.

RecipeMC improves recipe credibility by incorporating reward functions.

Generated recipes meet basic ingredient and dietary constraints more effectively.

Abstract

Automatic food recipe generation methods provide a creative tool for chefs to explore and to create new, and interesting culinary delights. Given the recent success of large language models (LLMs), they have the potential to create new recipes that can meet individual preferences, dietary constraints, and adapt to what is in your refrigerator. Existing research on using LLMs to generate recipes has shown that LLMs can be finetuned to generate realistic-sounding recipes. However, on close examination, these generated recipes often fail to meet basic requirements like including chicken as an ingredient in chicken dishes. In this paper, we propose RecipeMC, a text generation method using GPT-2 that relies on Monte Carlo Tree Search (MCTS). RecipeMC allows us to define reward functions to put soft constraints on text generation and thus improve the credibility of the generated recipes. Our results show that human evaluators prefer recipes generated with RecipeMC more often than recipes generated with other baseline methods when compared with real recipes.