Extremely large pre-trained language models (PTMs) such as GPT-3 are usually released as a service, allowing users to design task-specific prompts to query the PTMs through some black-box APIs. In such a scenario, which we call Language-Model-as-a-Service (LMaaS), gradients of the PTMs are usually not available. Can we optimize the task prompts by only accessing the model inference APIs? Based on recent observations that large PTMs have a very low intrinsic dimensionality, this work proposes the Black-Box Tuning to optimize PTMs through derivative-free algorithms. In particular, we invoke the CMA-ES to optimize the continuous prompt prepended to the input text by iteratively calling PTM inference APIs. Our experimental results demonstrate that, black-box tuning with RoBERTa on a few labeled samples not only significantly outperforms manual prompt and GPT-3's in-context learning, but also surpasses the gradient-based counterparts, namely prompt tuning and full model tuning.

本文提出黑盒优化框架来通过无导数优化预定义的任务提示，从而在使用预训练语言模型的服务化环境中实现更好的性能。在随机生成的子空间中进行优化，使得黑盒优化框架可以在 RoBERTa 上优化任务提示，并在少量标记样本上显着优于手动提示和 GPT-3 的上下文学习以及梯度优化方法。

语言模型即服务的黑盒调整