Abstract
Standardizing food terms from product labels and menus into ontology concepts is a prerequisite for trustworthy dietary assessment and safety reporting. The dominant approach to Named Entity Linking (NEL) in the food and nutrition domains fine-tunes Large Language Models (LLMs) on task-specific corpora. Although effective, fine-tuning incurs substantial computational cost, ties models to a particular ontology snapshot (i.e., version), and degrades under ontology drift. This paper presents FoodOntoRAG, a model- and ontology-agnostic pipeline that performs few-shot NEL by retrieving candidate entities from domain ontologies and conditioning an LLM on structured evidence (food labels, synonyms, definitions, and relations). A hybrid lexical--semantic retriever enumerates candidates; a selector agent chooses a best match with rationale; a separate scorer agent calibrates confidence; and, when confidence falls below a threshold, a synonym generator agent proposes reformulations to re-enter the loop. The pipeline approaches state-of-the-art accuracy while revealing gaps and inconsistencies in existing annotations. The design avoids fine-tuning, improves robustness to ontology evolution, and yields interpretable decisions through grounded justifications.
Abstract (translated)
将食品标签和菜单上的食品术语标准化为本体概念是进行可信的膳食评估和安全报告的前提。在食品和营养领域，命名实体链接（Named Entity Linking，NEL）的主要方法是对大型语言模型（LLMs）使用特定任务的数据集进行微调。尽管这种方法有效，但它会带来显著的计算成本，并且将模型绑定到某个特定版本的本体上，在面对本体漂移时性能会下降。 本文介绍了一种名为FoodOntoRAG的技术，它是一个与模型和本体无关的管道，通过从领域本体中检索候选实体并让LLM基于结构化证据（食品标签、同义词、定义及关系）进行微调来执行少样本NEL。这一技术采用了混合词汇-语义检索器来枚举候选实体；选择代理根据理由选择最佳匹配项；一个独立的评分代理调整信心水平；当自信度低于某个阈值时，同义词生成代理会提出替换方案以重新进入循环。 该管道在达到当前最先进的准确性的同时，揭示了现有注释中的缺口和不一致之处。其设计避免了微调过程，提高了对本体演变的鲁棒性，并通过基于事实的理由提供了可解释性的决策。
URL
https://arxiv.org/abs/2603.09758
