Saved in:
Bibliographic Details
Main Authors: Vavken, Maks Požarnik, Ogrinc, Matevž, Eftimov, Tome, Seljak, Barbara Koroušić
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09704
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917332773765120
author Vavken, Maks Požarnik
Ogrinc, Matevž
Eftimov, Tome
Seljak, Barbara Koroušić
author_facet Vavken, Maks Požarnik
Ogrinc, Matevž
Eftimov, Tome
Seljak, Barbara Koroušić
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09704
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluation of LLMs in retrieving food and nutritional context for RAG systems
Vavken, Maks Požarnik
Ogrinc, Matevž
Eftimov, Tome
Seljak, Barbara Koroušić
Computation and Language
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.
title Evaluation of LLMs in retrieving food and nutritional context for RAG systems
topic Computation and Language
url https://arxiv.org/abs/2603.09704