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

WARP: Word-level Adversarial ReProgramming

About

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific layers on top of the language model. In this paper, we present an alternative approach based on adversarial reprogramming, which extends earlier work on automatic prompt generation. Adversarial reprogramming attempts to learn task-specific word embeddings that, when concatenated to the input text, instruct the language model to solve the specified task. Using up to 25K trainable parameters per task, this approach outperforms all existing methods with up to 25M trainable parameters on the public leaderboard of the GLUE benchmark. Our method, initialized with task-specific human-readable prompts, also works in a few-shot setting, outperforming GPT-3 on two SuperGLUE tasks with just 32 training samples.

Karen Hambardzumyan, Hrant Khachatrian, Jonathan May• 2021

Related benchmarks

TaskDatasetResultRank
Natural Language UnderstandingGLUE (dev)
SST-2 (Acc)96
504
Natural Language UnderstandingGLUE (test)
SST-2 Accuracy96.3
416
Text ClassificationAG News (test)
Accuracy86.54
210
Natural Language UnderstandingGLUE (val)
SST-296
170
Named Entity RecognitionCoNLL English 2003 (test)--
135
Text ClassificationYahoo! Answers (test)
Clean Accuracy63.48
133
Topic ClassificationDBPedia (test)
Accuracy93.69
64
Entity TypingFewNERD (test)
Mean Accuracy59.23
52
Topic ClassificationAG's News (test)
CACC80.57
43
Named Entity RecognitionCoNLL English 2003 (val)
Micro-F189.89
19
Showing 10 of 14 rows

Other info

Code

Follow for update