Summarization for Generative Relation Extraction in the Microbiome Domain (2506.08647v1)

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 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.