There have been growing concerns regarding the out-of-domain generalization ability of natural language processing (NLP) models, particularly in question-answering (QA) tasks. Current synthesized data augmentation methods for QA are hampered by increased training costs. To address this issue, we propose a novel approach that combines prompting methods and linear probing then fine-tuning strategy, which does not entail additional cost. Our method has been theoretically and empirically shown to be effective in enhancing the generalization ability of both generative and discriminative models. Our approach outperforms state-of-the-art baselines, with an average increase in F1 score of 4.5%-7.9%. Furthermore, our method can be easily integrated into any pre-trained models and offers a promising solution to the under-explored cross-domain QA task. We release our source code at GitHub*.

翻译：自然语言处理（NLP）模型在域外泛化能力方面日益受到关注，尤其是在问答（QA）任务中。当前针对QA任务的合成数据增强方法受限于训练成本增加的问题。为解决此问题，我们提出了一种结合提示方法（prompting methods）与线性探测后微调（linear probing then fine-tuning）策略的新型方法，该方法无需额外成本。我们的方法在理论上和实验上均被证明能有效提升生成式模型和判别式模型的泛化能力。该方法在F1分数上平均提升4.5%-7.9%，优于现有最先进的基线模型。此外，我们的方法可轻松集成至任何预训练模型，并为尚未充分探索的跨领域QA任务提供了有前景的解决方案。我们在GitHub*上发布了源代码。