What can large language models do for sustainable food?
This addresses the problem of high greenhouse gas emissions from food systems for sustainability researchers and practitioners, though it is incremental in applying existing LLMs to new tasks.
The paper investigates how Large Language Models (LLMs) can reduce environmental impacts in food production, finding that LLMs can cut time by 45% in protein design tasks but produce suboptimal solutions in menu design, and proposes a framework integrating LLMs with optimization to decrease emissions by 79% while maintaining satisfaction.
Food systems are responsible for a third of human-caused greenhouse gas emissions. We investigate what Large Language Models (LLMs) can contribute to reducing the environmental impacts of food production. We define a typology of design and prediction tasks based on the sustainable food literature and collaboration with domain experts, and evaluate six LLMs on four tasks in our typology. For example, for a sustainable protein design task, food science experts estimated that collaboration with an LLM can reduce time spent by 45% on average, compared to 22% for collaboration with another expert human food scientist. However, for a sustainable menu design task, LLMs produce suboptimal solutions when instructed to consider both human satisfaction and climate impacts. We propose a general framework for integrating LLMs with combinatorial optimization to improve reasoning capabilities. Our approach decreases emissions of food choices by 79% in a hypothetical restaurant while maintaining participants' satisfaction with their set of choices. Our results demonstrate LLMs' potential, supported by optimization techniques, to accelerate sustainable food development and adoption.