The Power of Scale for Parameter-Efficient Prompt Tuning
The Power of Scale for Parameter-Efficient Prompt Tuning
复制标题
DOI：
10.18653/v1/2021.emnlp-main.243
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Brian Lester;Rami Al-Rfou;Noah Constant
中科院分区：
文献类型：
--
作者：
Brian Lester;Rami Al-Rfou;Noah Constant
在这项工作中，我们探索了“提示调整”，这是一种学习“软提示”的简单而有效的机制，可以调节冻结的语言模型以执行特定的下游任务。并可以调整以从任何标记的示例中纳入信号。调整变得更具竞争力：随着模型超过数十亿个参数，我们的方法“闭合差距”，并符合模型调整的强大性能（其中所有模型权重都已调节）。服务和重复使用一个冷冻模型来进行多个下游任务的能力可以缓解我们的方法。其他类似的方法。我们最终表明，以软提示为稳健性的供您供应域转移，并有效地“及时结合”。
In this work, we explore “prompt tuning,” a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signals from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3’s few-shot learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method “closes the gap” and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant because large models are costly to share and serve and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed “prefix tuning” of Li and Liang (2021) and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer and enables efficient “prompt ensembling.” We release code and model checkpoints to reproduce our experiments.