Instance-aware Prompt Learning for Language Understanding and Generation
This addresses the need for more adaptive prompt learning in NLP tasks, offering a novel approach to handle sample diversity, though it is incremental as it builds on existing prompt learning paradigms.
The paper tackles the problem of fixed prompts in prompt learning for pre-trained language models, which assume all samples in a task share the same prompt despite diversity in difficulty, by proposing an instance-aware prompt learning method that learns a different prompt for each instance, resulting in state-of-the-art performance on the SuperGLUE few-shot learning benchmark.
Recently, prompt learning has become a new paradigm to utilize pre-trained language models (PLMs) and achieves promising results in downstream tasks with a negligible increase of parameters. The current usage of discrete and continuous prompts assumes that the prompt is fixed for a specific task and all samples in the task share the same prompt. However, a task may contain quite diverse samples in which some are easy and others are difficult, and diverse prompts are desirable. In this paper, we propose an instance-aware prompt learning method that learns a different prompt for each instance. Specifically, we suppose that each learnable prompt token has a different contribution to different instances, and we learn the contribution by calculating the relevance score between an instance and each prompt token. The contribution weighted prompt would be instance aware. We apply our method to both unidirectional and bidirectional PLMs on both language understanding and generation tasks. Extensive experiments demonstrate that our method obtains considerable improvements compared to strong baselines. Especially, our method achieves the state-of-the-art on the SuperGLUE few-shot learning benchmark.