Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation

TL;DR

This paper presents the Swiss Food Knowledge Graph, a comprehensive resource integrating recipes, ingredients, and nutritional data to improve context-aware nutrition recommendations using LLMs and a novel enrichment pipeline.

Contribution

It introduces the first Swiss-specific food knowledge graph combining diverse nutrition-related data and establishes a benchmark for LLM-based knowledge augmentation in this domain.

Findings

LLMs effectively enrich the food knowledge graph with relevant nutritional data.

The SwissFKG supports detailed ingredient-level information, including allergens and dietary restrictions.

Graph-RAG application demonstrates improved user-specific nutrition query responses.

Abstract

AI has driven significant progress in the nutrition field, especially through multimedia-based automatic dietary assessment. However, existing automatic dietary assessment systems often overlook critical non-visual factors, such as recipe-specific ingredient substitutions that can significantly alter nutritional content, and rarely account for individual dietary needs, including allergies, restrictions, cultural practices, and personal preferences. In Switzerland, while food-related information is available, it remains fragmented, and no centralized repository currently integrates all relevant nutrition-related aspects within a Swiss context. To bridge this divide, we introduce the Swiss Food Knowledge Graph (SwissFKG), the first resource, to our best knowledge, to unite recipes, ingredients, and their substitutions with nutrient data, dietary restrictions, allergen information, and national nutrition guidelines under one graph. We establish a LLM-powered enrichment pipeline for populating the graph, whereby we further present the first benchmark of four off-the-shelf (<70 B parameter) LLMs for food knowledge augmentation. Our results demonstrate that LLMs can effectively enrich the graph with relevant nutritional information. Our SwissFKG goes beyond recipe recommendations by offering ingredient-level information such as allergen and dietary restriction information, and guidance aligned with nutritional guidelines. Moreover, we implement a Graph-RAG application to showcase how the SwissFKG's rich natural-language data structure can help LLM answer user-specific nutrition queries, and we evaluate LLM-embedding pairings by comparing user-query responses against predefined expected answers. As such, our work lays the foundation for the next generation of dietary assessment tools that blend visual, contextual, and cultural dimensions of eating.