Contrastive Demonstration Tuning for Pre-trained Language Models
This work addresses the problem of optimizing demonstrations for prompt-tuning in low-data scenarios, offering an incremental improvement for NLP practitioners.
The paper tackles the limited study of demonstration examples in prompt-tuning for pre-trained language models by proposing contrastive demonstration tuning, a pluggable and extensible approach that eliminates demonstration sampling and improves performance when integrated with existing methods like LM-BFF and P-tuning, as shown on 16 datasets.
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searching discrete or continuous prompts or optimized verbalizers, yet studies for the demonstration are still limited. Concretely, the demonstration examples are crucial for an excellent final performance of prompt-tuning. In this paper, we propose a novel pluggable, extensible, and efficient approach named contrastive demonstration tuning, which is free of demonstration sampling. Furthermore, the proposed approach can be: (i) Plugged into any previous prompt-tuning approaches; (ii) Extended to widespread classification tasks with a large number of categories. Experimental results on 16 datasets illustrate that our method integrated with previous approaches LM-BFF and P-tuning can yield better performance. Code is available in https://github.com/zjunlp/PromptKG/tree/main/research/Demo-Tuning.