arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09704cs.CL
收藏

对LLMs在RAG系统中检索食物和营养上下文的评估

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

Department of Computer Systems Institute "Jožef Stefan"(计算机系统研究所(Jožef Stefan)部门)

Maks Požarnik Vavken, Matevž Ogrinc, Tome Eftimov, Barbara Koroušić Seljak

AI总结:

本文评估了LLMs在RAG系统中检索食物和营养信息的能力,发现其在可表达约束下表现良好,但在复杂约束下存在局限。

摘要:

在本文中,我们评估了四种大型语言模型(LLMs)在其在专门的检索增强生成(RAG)系统中检索数据的有效性,使用了一个全面的食物组成数据库。我们的方法聚焦于LLMs将自然语言查询转换为结构化元数据过滤器的能力,从而通过Chroma向量数据库实现高效检索。通过在这一关键检索步骤中实现高精度,我们证明LLMs可以作为易于获取、高性能的工具,大幅减少之前需要领域专家(如食物编纂员和营养师)来利用复杂食物和营养数据所必需的手动努力和技术专长。然而,尽管在简单和中等复杂性查询上表现优异,我们的分析显示,当查询涉及非可表达约束时,可靠的检索仍具挑战性。这些发现表明,当约束可以明确表达时,LLM驱动的元数据过滤表现优异,但当查询超出元数据格式的表示范围时则面临困难。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑