Summarization for Generative Relation Extraction in the Microbiome Domain

2025/06/10 by Oumaima El Khettari, Khettari, Oumaima El, Solen Quiniou +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Bioinformatics #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2506.08647

openalex publication_date 2025/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We explore a generative relation extraction (RE) pipeline tailored to the study of interactions in the intestinal microbiome, a complex and low-resource biomedical domain. Our method leverages summarization with large language models (LLMs) to refine context before extracting relations via instruction-tuned generation. Preliminary results on a dedicated corpus show that summarization improves generative RE performance by reducing noise and guiding the model. However, BERT-based RE approaches still outperform generative models. This ongoing work demonstrates the potential of generative methods to support the study of specialized domains in low-resources setting.

Citations

• A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models
• The Llama 3 Herd of Models
• Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting
• MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation
• Revisiting Large Language Models as Zero-shot Relation Extractors
• Summarization is (Almost) Dead
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Building a Corpus for Biomedical Relation Extraction of Species Mentions
• Revisiting Relation Extraction in the era of Large Language Models
• News Summarization and Evaluation in the Era of GPT-3
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents

Cited by

• Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges

Related

• Biomedical relation extraction with pre-trained language representations\n and minimal task-specific architecture
• Building a Corpus for Biomedical Relation Extraction of Species Mentions
• An Empirical Study on Relation Extraction in the Biomedical Domain
• Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique Identifier
• BactInt: A domain driven transfer learning approach and a corpus for extracting inter-bacterial interactions from biomedical text