Evaluation of LLMs in retrieving food and nutritional context for RAG systems

TL;DR

This study evaluates four LLMs for their ability to retrieve food and nutrition data in a RAG system, highlighting their strengths in handling explicit queries and limitations with complex, non-expressible constraints.

Contribution

It demonstrates the effectiveness of LLMs in translating natural language into metadata filters for food data retrieval, reducing manual effort for domain experts.

Findings

High accuracy in easy and moderate queries

Challenges with complex, non-expressible constraints

LLMs are effective for explicit metadata filtering

Abstract

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.