Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAG

2026-03-10

AI Summary

This work addresses the challenge of performance degradation and high costs associated with fine-tuning approaches for standardizing food labels and menu terminology, which often suffer from ontology drift. To overcome this, the authors propose FoodOntoRAG—a tuning-free, ontology-agnostic entity linking framework that leverages retrieval-augmented generation (RAG) to guide large language models in few-shot reasoning. The framework integrates a hybrid lexical–semantic retriever with a multi-agent mechanism comprising a selector, a confidence scorer, and a synonym generator. FoodOntoRAG achieves near-optimal accuracy while significantly enhancing robustness to ontology evolution, offering an interpretable and traceable decision process, and uncovering inconsistencies in existing annotations.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Natural Language Processing: Safety and Robustness
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Food Entity Linking
• Ontology Drift
• Named Entity Linking
• Food Ontology
• Robustness

Innovation

• FoodOntoRAG
• ontology drift
• retrieval-augmented generation
• few-shot entity linking
• interpretable NEL