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

TL;DR

FoodOntoRAG is a novel, ontology-agnostic pipeline for food entity linking that uses retrieval and reasoning to improve robustness and interpretability without fine-tuning models.

Contribution

It introduces a few-shot, retrieval-based approach for food entity linking that handles ontology drift and enhances interpretability, avoiding costly fine-tuning.

Findings

Approaches state-of-the-art accuracy in food entity linking

Improves robustness to ontology updates

Provides interpretable, justified decisions

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.