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.- Anthology ID:
- 2023.findings-acl.50
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 794–812
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.50
- DOI:
- 10.18653/v1/2023.findings-acl.50
- Cite (ACL):
- Kai Zhang, Bernal Jimenez Gutierrez, and Yu Su. 2023. Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors. In Findings of the Association for Computational Linguistics: ACL 2023, pages 794–812, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors (Zhang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.50.pdf