Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Abstract

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering. The main principle behind this approach involves reformulating potential natural language processing tasks into the task of a pre-trained language model and differentially optimizing the prompt template as well as the target label with backpropagation. Furthermore, the proposed approach can be: (i) Plugged to any pre-trained language models; (ii) Extended to widespread classification tasks. A comprehensive evaluation of standard NLP tasks demonstrates that the proposed approach achieves a better few-shot performance. Code is available in https://github.com/zjunlp/DART.

Accepted by ICLR 2022

References in corpus (11)

• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
• Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
• True Few-Shot Learning with Language Models
• Making Pre-trained Language Models Better Few-shot Learners
• Entailment as Few-Shot Learner
• Calibrate Before Use: Improving Few-Shot Performance of Language Models
• PTR: Prompt Tuning with Rules for Text Classification
• Factual Probing Is [MASK]: Learning vs. Learning to Recall

Cited by in corpus (8)

• The Creativity of Text-to-Image Generation
• P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
• No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence
• An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
• The Rise of Artificial Intelligence in Educational Measurement: Opportunities and Ethical Challenges
• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
• Ontology-enhanced Prompt-tuning for Few-shot Learning
• SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis