A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models

TL;DR

This paper explores using large language models with few-shot learning and structured prompts to improve relation extraction for scientific knowledge graphs in new domains, requiring minimal expert annotation.

Contribution

It demonstrates a novel few-shot, schema-constrained approach leveraging LLMs for domain adaptation in relation extraction with minimal annotation.

Findings

Significant performance improvement over off-domain baseline models

Effective schema-constrained data annotation with minimal expert input

Potential for scalable domain adaptation in scientific KG generation

Abstract

Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations between domain entities in text. While these relations are fully applicable across scientific areas, existing models are trained on few domain-specific datasets such as SciERC and do not perform well on new target domains. In this paper, we experiment with leveraging in-context learning capabilities of Large Language Models to perform schema-constrained data annotation, collecting in-domain training instances for a Transformer-based relation extraction model deployed on titles and abstracts of research papers in the Architecture, Construction, Engineering and Operations (AECO) domain. By assessing the performance gain with respect to a baseline Deep Learning architecture trained on off-domain data, we show that by using a few-shot learning strategy with structured prompts and only minimal expert annotation the presented approach can potentially support domain adaptation of a science KG generation model.