LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification

Jing Zhang, Hui Gao, Peng Zhang, Boda Feng, Wenmin Deng, Yuexian Hou


Abstract
The few-shot tasks require the model to have the ability to generalize from a few samples. However, due to the lack of cognitive ability, the current works cannot fully utilize limited samples to expand the sample space and still suffer from overfitting issues. To address the problems, we propose a LLM-Augmented Unsupervised Contrastive Learning Framework (LA-UCL), which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation, and presents corresponding contrastive learning strategies. Specifically, in the self-augmented contrastive learning module, we construct a retrieval-based in-context prompt scheme by retrieving similar but different category data from the original samples, guiding the LLM to generate more discriminative augmented data. Then, by designing group-level contrastive loss to enhance the model’s discriminative ability. In the external-augmented contrastive learning module, we utilize web knowledge retrieval to expand the sample space and leverage LLM to generate more diverse data, and introduce sample-level contrastive loss for unlabeled data to improve the model’s generalization. Experimental results on six datasets show that our model exceeds the baseline models.
Anthology ID:
2024.lrec-main.890
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
10198–10207
Language:
URL:
https://aclanthology.org/2024.lrec-main.890
DOI:
Bibkey:
Cite (ACL):
Jing Zhang, Hui Gao, Peng Zhang, Boda Feng, Wenmin Deng, and Yuexian Hou. 2024. LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10198–10207, Torino, Italia. ELRA and ICCL.
Cite (Informal):
LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification (Zhang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.890.pdf