Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition

Wei Chen, Lili Zhao, Zhi Zheng, Tong Xu, Yang Wang, Enhong Chen


Abstract
Recently, few-shot Named Entity Recognition (NER) has attracted significant attention due to the high cost of obtaining high-quality labeled data. Decomposition-based methods have demonstrated remarkable performance on this task, which initially train a type-independent span detector and subsequently classify the detected spans based on their types. However, this framework has an evident drawback as a domain-agnostic detector cannot ensure the identification of only those entity spans that are specific to the target domain. To address this issue, we propose Double-Checker, which leverages collaboration between Large Language Models (LLMs) and small models. Specifically, we employ LLMs to verify candidate spans predicted by the small model and eliminate any spans that fall outside the scope of the target domain. Extensive experiments validate the effectiveness of our method, consistently yielding improvements over two baseline approaches. Our code is available at https://github.com/fanshu6hao/Double-Checker.
Anthology ID:
2024.findings-emnlp.180
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:
3172–3181
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.180/
DOI:
10.18653/v1/2024.findings-emnlp.180
Bibkey:
Cite (ACL):
Wei Chen, Lili Zhao, Zhi Zheng, Tong Xu, Yang Wang, and Enhong Chen. 2024. Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3172–3181, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition (Chen et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.180.pdf