Zero-Shot Document-Level Biomedical Relation Extraction via Scenario-based Prompt Design in Two-Stage with LLM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Lei, Kang, Ling, Guo, Quan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914348742475776
author Zhao, Lei
Kang, Ling
Guo, Quan
author_facet Zhao, Lei
Kang, Ling
Guo, Quan
contents With the advent of artificial intelligence (AI), many researchers are attempting to extract structured information from document-level biomedical literature by fine-tuning large language models (LLMs). However, they face significant challenges such as the need for expensive hardware, like high-performance GPUs and the high labor costs associated with annotating training datasets, especially in biomedical realm. Recent research on LLMs, such as GPT-4 and Llama3, has shown promising performance in zero-shot settings, inspiring us to explore a novel approach to achieve the same results from unannotated full documents using general LLMs with lower hardware and labor costs. Our approach combines two major stages: named entity recognition (NER) and relation extraction (RE). NER identifies chemical, disease and gene entities from the document with synonym and hypernym extraction using an LLM with a crafted prompt. RE extracts relations between entities based on predefined relation schemas and prompts. To enhance the effectiveness of prompt, we propose a five-part template structure and a scenario-based prompt design principles, along with evaluation method to systematically assess the prompts. Finally, we evaluated our approach against fine-tuning and pre-trained models on two biomedical datasets: ChemDisGene and CDR. The experimental results indicate that our proposed method can achieve comparable accuracy levels to fine-tuning and pre-trained models but with reduced human and hardware expenses.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01077
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Document-Level Biomedical Relation Extraction via Scenario-based Prompt Design in Two-Stage with LLM
Zhao, Lei
Kang, Ling
Guo, Quan
Neural and Evolutionary Computing
With the advent of artificial intelligence (AI), many researchers are attempting to extract structured information from document-level biomedical literature by fine-tuning large language models (LLMs). However, they face significant challenges such as the need for expensive hardware, like high-performance GPUs and the high labor costs associated with annotating training datasets, especially in biomedical realm. Recent research on LLMs, such as GPT-4 and Llama3, has shown promising performance in zero-shot settings, inspiring us to explore a novel approach to achieve the same results from unannotated full documents using general LLMs with lower hardware and labor costs. Our approach combines two major stages: named entity recognition (NER) and relation extraction (RE). NER identifies chemical, disease and gene entities from the document with synonym and hypernym extraction using an LLM with a crafted prompt. RE extracts relations between entities based on predefined relation schemas and prompts. To enhance the effectiveness of prompt, we propose a five-part template structure and a scenario-based prompt design principles, along with evaluation method to systematically assess the prompts. Finally, we evaluated our approach against fine-tuning and pre-trained models on two biomedical datasets: ChemDisGene and CDR. The experimental results indicate that our proposed method can achieve comparable accuracy levels to fine-tuning and pre-trained models but with reduced human and hardware expenses.
title Zero-Shot Document-Level Biomedical Relation Extraction via Scenario-based Prompt Design in Two-Stage with LLM
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.01077