Evaluation of LLMs in retrieving food and nutritional context for RAG systems
This work addresses the problem of reducing manual effort for domain experts like nutritionists in accessing complex food data, though it is incremental as it applies existing methods to a new domain.
The paper evaluated four LLMs for retrieving food and nutritional data in a RAG system, achieving high accuracy in translating natural language queries into structured metadata filters, but found challenges with difficult queries involving non-expressible constraints.
In this article, we evaluate four Large Language Models (LLMs) and their effectiveness at retrieving data within a specialized Retrieval-Augmented Generation (RAG) system, using a comprehensive food composition database. Our method is focused on the LLMs ability to translate natural language queries into structured metadata filters, enabling efficient retrieval via a Chroma vector database. By achieving high accuracy in this critical retrieval step, we demonstrate that LLMs can serve as an accessible, high-performance tool, drastically reducing the manual effort and technical expertise previously required for domain experts, such as food compilers and nutritionists, to leverage complex food and nutrition data. However, despite the high performance on easy and moderately complex queries, our analysis of difficult questions reveals that reliable retrieval remains challenging when queries involve non-expressible constraints. These findings demonstrate that LLM-driven metadata filtering excels when constraints can be explicitly expressed, but struggles when queries exceed the representational scope of the metadata format.