StablePT：通过输入分离实现少样本学习中稳定提示的方法
StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
AI总结：
本文提出StablePT方法，通过将硬提示与软提示分离输入并结合对比学习优化软提示，显著提升了少样本提示调优的准确率与稳定性。
摘要：
大型语言模型已经展现出通过提示成为高效少样本学习者的能力，彻底改变了数据稀缺条件下的学习范式。然而，这种方法在很大程度上依赖于提示初始化的质量，并且在不同的运行中总是表现出较大的变异性。这种特性使得提示调优高度不可靠，并且容易受到构造不佳的提示的影响，从而限制了其向更多实际应用的扩展。为了解决这一问题，我们提出将硬提示和软提示作为独立的输入进行处理，以减轻由提示初始化带来的噪声。此外，我们利用对比学习来优化软提示，从而在训练过程中利用类别感知信息以保持模型性能。实验结果表明，StablePT在准确率上比最先进的方法高出6.97%，并且平均将标准差降低了1.92。此外，大量实验强调了其在覆盖多种任务的8个数据集上的鲁棒性和稳定性。代码可在 https://github.com/lccc0528/Stable/tree/main 获取。
英文摘要：
Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt initialization, and always exhibits large variability among different runs. Such property makes prompt tuning highly unreliable and vulnerable to poorly constructed prompts, which limits its extension to more real-world applications. To tackle this issue, we propose to treat the hard prompt and soft prompt as separate inputs to mitigate noise brought by the prompt initialization. Furthermore, we optimize soft prompts with contrastive learning for utilizing class-aware information in the training process to maintain model performance. Experimental results demonstrate that \sysname outperforms state-of-the-art methods by 6.97% in accuracy and reduces the standard deviation by 1.92 on average. Furthermore, extensive experiments underscore its robustness and stability across 8 datasets covering various tasks. Codes are available at https://github.com/lccc0528/Stable/tree/main.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
