A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models
Abstract
Extracting relations from scientific literature is a fundamental task in biomedical NLP because entities and relations among them drive hypothesis generation and knowledge discovery. As literature grows rapidly, relation extraction (RE) is indispensable to curate knowledge graphs to be used as computable structured and symbolic representations. With the rise of LLMs, it is pertinent to examine if it is better to skip tailoring supervised RE methods, save annotation burden, and just use zero shot RE (ZSRE) via LLM API calls. In this paper, we propose a benchmark with seven biomedical RE datasets with interesting characteristics and evaluate three Open AI models (GPT-4, o1, and GPT-OSS-120B) for end-to-end ZSRE. We show that LLM-based ZSRE is inching closer to supervised methods in performances on some datasets but still struggles on complex inputs expressing multiple relations with different predicates. Our error analysis reveals scope for improvements.
Cite
@article{arxiv.2504.04083,
title = {A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models},
author = {Aviv Brokman and Xuguang Ai and Yuhang Jiang and Shashank Gupta and Ramakanth Kavuluru},
journal= {arXiv preprint arXiv:2504.04083},
year = {2026}
}
Comments
Accepted to appear in proceedings of the 3rd Workshop on Artificial Intelligence for Scientific Publications (WASP@AACL 2025). Code and data are available here: https://github.com/bionlproc/ZeroShotRE