How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?

TL;DR

This paper explores how large language models like GPT-3.5 can be effectively used for few-shot relation extraction, proposing methods to improve performance and achieve state-of-the-art results.

Contribution

It systematically investigates in-context learning and data generation techniques, introducing task instructions and schema constraints to enhance few-shot relation extraction.

Findings

In-context learning performs comparably to prompt learning methods.

Data generation with large language models improves performance significantly.

Achieves new state-of-the-art results on four relation extraction datasets.

Abstract

Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models. In this paper, we investigate principal methodologies, in-context learning and data generation, for few-shot relation extraction via GPT-3.5 through exhaustive experiments. To enhance few-shot performance, we further propose task-related instructions and schema-constrained data generation. We observe that in-context learning can achieve performance on par with previous prompt learning approaches, and data generation with the large language model can boost previous solutions to obtain new state-of-the-art few-shot results on four widely-studied relation extraction datasets. We hope our work can inspire future research for the capabilities of large language models in few-shot relation extraction. Code is available in https://github.com/zjunlp/DeepKE/tree/main/example/llm.