Enhancing the zero-shot performance of instruction-following models requires heavy computation, either by scaling the total number of training datasets or the model size. In this work, we explore how retrieval of soft prompts obtained through prompt tuning can efficiently assist hard prompts in zero-shot task generalization. Specifically, we train soft prompt embeddings for each prompt through prompt tuning, store the samples of the training instances mapped with the prompt embeddings, and retrieve the corresponding prompt embedding of the training instance closest to the query instance during inference. While only adding 0.007% additional parameters, retrieval of soft prompt enhances the performance of T0 on unseen tasks by outperforming it on 10 out of 11 datasets as well as improving the mean accuracy of T0 on BIG-bench benchmark by 2.39% points. Also, we report an interesting finding that retrieving source embeddings trained on similar answer choice formats is more important than those on similar task types.

翻译：提升指令跟随模型的零样本性能通常需要大量计算资源，无论是通过扩展训练数据集规模还是增加模型参数量。本研究探索如何通过提示微调获取的软提示检索，有效辅助硬提示实现零样本任务泛化。具体而言，我们为每个提示通过提示微调训练软提示嵌入，将训练实例样本与提示嵌入关联存储，在推理阶段检索与查询实例最接近的训练实例对应的提示嵌入。仅增加0.007%的额外参数，软提示检索即可使T0在11个数据集的10个未见过任务上表现更优，并将T0在BIG-bench基准上的平均准确率提升2.39个百分点。此外，我们发现一个有趣现象：检索基于相似答案选择格式训练的源嵌入比检索基于相似任务类型的嵌入更为重要。