Recommending Healthy and Sustainable Meals exploiting Food Retrieval and Large Language Models

Given the rising global concerns about healthy nutrition and environmental sustainability, individuals need more and more support in making good choices concerning their daily meals. To this end, in this paper we introduce HeaSE, a framework for Healthy And Sustainable Eating. Given an input recipe, HeaSE identifies healthier and more sustainable meals by exploiting retrieval techniques and large language models. The framework works in two steps. First, it uses food retrieval strategies based on macro-nutrient information to identify candidate alternative meals. This ensures that the substitutions maintain a similar nutritional profile. Next, HeaSE employs large language models to re-rank these potential replacements while considering factors beyond just nutrition, such as the recipe’s environmental impact. In the experimental evaluation, we showed the capabilities of LLMs in identifying more sustainable and healthier alternatives within a set of candidate options. This highlights the potential of these models to guide users towards food choices that are both nutritious and environmentally responsible.