Automated Few-Shot Classification with Instruction-Finetuned Language Models

Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Wilson


Abstract
A particularly successful class of approaches for few-shot learning combines language models with prompts - hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires domain knowledge and substantial guesswork. We observe, in the context of classification tasks, that instruction finetuned language models are remarkably robust towards some dimensions of a prompt’s design. We subsequently propose a simple method to eliminate the need for handcrafted prompts, named AuT-Few. This approach consists of (i) a prompt retrieval module that selects suitable task instructions from the instruction-tuning knowledge base, and (ii) the generation of two distinct, semantically meaningful, class descriptions and a selection mechanism via cross-validation. Over 12 datasets, spanning 8 classification tasks, we show that AuT-Few outperforms current state-of-the-art few-shot learning methods. Moreover, AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark. Notably, these results are achieved without task-specific handcrafted prompts on unseen tasks.
Anthology ID:
2023.findings-emnlp.158
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2414–2432
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.158
DOI:
10.18653/v1/2023.findings-emnlp.158
Bibkey:
Cite (ACL):
Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, and Andrew Wilson. 2023. Automated Few-Shot Classification with Instruction-Finetuned Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2414–2432, Singapore. Association for Computational Linguistics.
Cite (Informal):
Automated Few-Shot Classification with Instruction-Finetuned Language Models (Aly et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.158.pdf