Abstract
The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF—better few-shot fine-tuning of language models—a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning.- Anthology ID:
- 2021.acl-long.295
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3816–3830
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.295
- DOI:
- 10.18653/v1/2021.acl-long.295
- Cite (ACL):
- Tianyu Gao, Adam Fisch, and Danqi Chen. 2021. Making Pre-trained Language Models Better Few-shot Learners. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3816–3830, Online. Association for Computational Linguistics.
- Cite (Informal):
- Making Pre-trained Language Models Better Few-shot Learners (Gao et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.acl-long.295.pdf
- Code
- princeton-nlp/LM-BFF + additional community code
- Data
- AG News, CoLA, GLUE, MPQA Opinion Corpus, MRPC, MultiNLI, QNLI, SNLI, SST, SST-2, SST-5