LLM as a metric critic for low resource relation identification

Zhe Yang, Yi Huang, Yaqin Chen, Xiaoting Wu, Junlan Feng, Chao Deng


Abstract
In extremely low resource relation identification scenario, small language models (SLMs) incline to overfit, which significantly diminishes their accuracy. Recently, large language models (LLMs) are gradually applied to classification tasks with converting original objective into the generation task via in-context learning. However, abundance of the classifier categories poses challenges in selecting demonstrations. Moreover, the mapping between category labels and textual descriptions requires expensive expert knowledge, thereby constraining the efficacy of in-context learning for LLMs. We uphold that SLM is optimal for handling classification tasks, and its shortcomings in the low resource setting can be mitigated by leveraging LLM. Hence, we propose a co-evolution strategy on SLM & LLM for relation identification. Specifically, LLM provides essential background knowledge to assist training process of the SLM classifier, while evaluation metrics from the classifier, in turn, offer valuable insights to refine the generation prompts of the LLM. We conduct experiments on several datasets which demonstrates preponderance of the proposed model.
Anthology ID:
2024.findings-emnlp.828
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:
14168–14178
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.828/
DOI:
10.18653/v1/2024.findings-emnlp.828
Bibkey:
Cite (ACL):
Zhe Yang, Yi Huang, Yaqin Chen, Xiaoting Wu, Junlan Feng, and Chao Deng. 2024. LLM as a metric critic for low resource relation identification. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14168–14178, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LLM as a metric critic for low resource relation identification (Yang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.828.pdf
Software:
 2024.findings-emnlp.828.software.zip