Paper
Evaluation of LLMs in retrieving food and nutritional context for RAG systems
Authors
Maks Požarnik Vavken, Matevž Ogrinc, Tome Eftimov, Barbara Koroušić Seljak
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.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.09704v1</id>\n <title>Evaluation of LLMs in retrieving food and nutritional context for RAG systems</title>\n <updated>2026-03-10T14:15:35Z</updated>\n <link href='https://arxiv.org/abs/2603.09704v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.09704v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-03-10T14:15:35Z</published>\n <arxiv:comment>This is the preprint for our conference paper for IEEE International Conference on Big Data</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Maks Požarnik Vavken</name>\n </author>\n <author>\n <name>Matevž Ogrinc</name>\n </author>\n <author>\n <name>Tome Eftimov</name>\n </author>\n <author>\n <name>Barbara Koroušić Seljak</name>\n </author>\n <arxiv:doi>10.1109/BigData66926.2025.11401545</arxiv:doi>\n <link href='https://doi.org/10.1109/BigData66926.2025.11401545' rel='related' title='doi'/>\n </entry>"
}