Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting

Siyi Liu, Yang Li, Jiang Li, Shan Yang, Yunshi Lan


Abstract
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-specific prompts needed for understanding various sentences and relations. To address this, we introduce the Self-Prompting framework, a novel method designed to fully harness the embedded RE knowledge within LLMs. Specifically, our framework employs a three-stage diversity approach to prompt LLMs, generating multiple synthetic samples that encapsulate specific relations from scratch. These generated samples act as in-context learning samples, offering explicit and context-specific guidance to efficiently prompt LLMs for RE. Experimental evaluations on benchmark datasets show our approach outperforms existing LLM-based zero-shot RE methods. Additionally, our experiments confirm the effectiveness of our generation pipeline in producing high-quality synthetic data that enhances performance.
Anthology ID:
2024.findings-emnlp.769
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13147–13161
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.769/
DOI:
10.18653/v1/2024.findings-emnlp.769
Bibkey:
Cite (ACL):
Siyi Liu, Yang Li, Jiang Li, Shan Yang, and Yunshi Lan. 2024. Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13147–13161, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting (Liu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.769.pdf