Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors

TL;DR

This paper introduces QA4RE, a framework that aligns relation extraction with question answering tasks, significantly enhancing large language models' zero-shot performance on RE by leveraging common instruction-tuning datasets.

Contribution

The paper proposes QA4RE, a novel approach that improves zero-shot relation extraction in LLMs by aligning it with question answering, addressing the low representation of RE in instruction datasets.

Findings

QA4RE consistently improves LLM zero-shot RE performance

LLMs outperform strong zero-shot baselines with QA4RE

Framework shows robustness and transferability

Abstract

Recent work has shown that fine-tuning large language models (LLMs) on large-scale instruction-following datasets substantially improves their performance on a wide range of NLP tasks, especially in the zero-shot setting. However, even advanced instruction-tuned LLMs still fail to outperform small LMs on relation extraction (RE), a fundamental information extraction task. We hypothesize that instruction-tuning has been unable to elicit strong RE capabilities in LLMs due to RE's low incidence in instruction-tuning datasets, making up less than 1% of all tasks (Wang et al., 2022). To address this limitation, we propose QA4RE, a framework that aligns RE with question answering (QA), a predominant task in instruction-tuning datasets. Comprehensive zero-shot RE experiments over four datasets with two series of instruction-tuned LLMs (six LLMs in total) demonstrate that our QA4RE framework consistently improves LLM performance, strongly verifying our hypothesis and enabling LLMs to outperform strong zero-shot baselines by a large margin. Additionally, we provide thorough experiments and discussions to show the robustness, few-shot effectiveness, and strong transferability of our QA4RE framework. This work illustrates a promising way of adapting LLMs to challenging and underrepresented tasks by aligning these tasks with more common instruction-tuning tasks like QA.