During zero-shot inference with language models (LMs), using hard prompts alone may not be able to fully describe the target task. In this paper, we explore how the retrieval of soft prompts obtained through prompt tuning can 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 (hard prompt + input instances) mapped with the prompt embeddings, and retrieve the corresponding prompt embedding of the training instance closest to the query instance during inference. Results show this simple approach 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 while adding only 0.007% additional parameters. Also, using interpolation of multiple embeddings and variance-based ranking further improve accuracy and robustness to different evaluation prompts, widening the performance gap. Finally, we find that retrieving source embeddings trained on similar answer choice formats is more important than those on similar task types. Model checkpoints and code implementation are available at https://github.com/seonghyeonye/RoSPr.

本文探索了通过提示调整获得的软提示如何在零样本推理中协助硬提示，以实现任务泛化。结果表明，此简单方法仅增加了0.007％的额外参数，但在大型基准测试上提高了2.39％的平均准确率，对不同评估提示的准确性和鲁棒性有更好的排名。

软提示检索增强零样本任务泛化能力