FoodSEM: Large Language Model Specialized in Food Named-Entity Linking

2025-09-26

AI Summary

Existing general-purpose or domain-specific large language models (LLMs) underperform on Food Named Entity Linking (NEL), failing to accurately map food mentions in text to ontology identifiers in resources such as FoodOn and SNOMED-CT. Method: We propose the first instruction-tuned LLM specifically for food NEL, integrating instruction fine-tuning with zero-shot and few-shot prompting to achieve high-precision cross-ontology entity alignment. Contribution/Results: We construct and publicly release the first LLM-fine-tuning corpus dedicated to food entity annotation. Experimental evaluation across multiple food NEL benchmarks demonstrates state-of-the-art performance, achieving up to 98% F1 score—substantially outperforming both unadapted LLM baselines and prior systems. This work establishes a strong, reproducible benchmark and methodological foundation for food semantic understanding.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper introduces FoodSEM, a state-of-the-art fine-tuned open-source large language model (LLM) for named-entity linking (NEL) to food-related ontologies. To the best of our knowledge, food NEL is a task that cannot be accurately solved by state-of-the-art general-purpose (large) language models or custom domain-specific models/systems. Through an instruction-response (IR) scenario, FoodSEM links food-related entities mentioned in a text to several ontologies, including FoodOn, SNOMED-CT, and the Hansard taxonomy. The FoodSEM model achieves state-of-the-art performance compared to related models/systems, with F1 scores even reaching 98% on some ontologies and datasets. The presented comparative analyses against zero-shot, one-shot, and few-shot LLM prompting baselines further highlight FoodSEM's superior performance over its non-fine-tuned version. By making FoodSEM and its related resources publicly available, the main contributions of this article include (1) publishing a food-annotated corpora into an IR format suitable for LLM fine-tuning/evaluation, (2) publishing a robust model to advance the semantic understanding of text in the food domain, and (3) providing a strong baseline on food NEL for future benchmarking.

Problem

• Linking food entities to ontologies using specialized LLM
• Addressing limitations of general models in food NEL
• Creating benchmark for semantic food text understanding

Innovation

• Fine-tuned LLM for food entity linking
• Links food entities to multiple ontologies
• Achieves 98% F1 score on datasets