Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Making Pre-trained Language Models Better Few-shot Learners

About

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.

Tianyu Gao, Adam Fisch, Danqi Chen• 2020

Related benchmarks

TaskDatasetResultRank
Natural Language InferenceSNLI (test)
Accuracy77.5
681
Natural Language UnderstandingGLUE
SST-295
452
Natural Language InferenceRTE
Accuracy80.9
367
Subjectivity ClassificationSubj
Accuracy97
266
Text ClassificationAG-News
Accuracy71.3
248
Text ClassificationSST-2 (test)
Accuracy79.9
185
Sentiment ClassificationSST-2
Accuracy95
174
Sentiment ClassificationMR
Accuracy90.8
148
Sentiment ClassificationCR
Accuracy89.4
142
Sentiment ClassificationMR (test)
Accuracy87.7
142
Showing 10 of 57 rows

Other info

Code

Follow for update