Prompt tuning recently becomes a hot-spot in the applications of large
pretrained language models on specific downstream tasks. Regarding the Language
Model as a Service (LMaaS), black-box tuning using derivative-free optimization
(DFO) provides a novel approach to expand the practical scenarios of pretrained
models and enrich the researches of few-shot learning. In this report, we
present our solution in this competition that is based on the LMaaS scenario.
Our solution consists of several modifications to BBTv2, including multiple
label words, selection of P0, rolling update strategy, multi-task loss from MLP
classifier, and finally using the ensemble method to further improve
generalization ability. We also shared some strategies that we tried but didn't
use in the final submission for further discussion. In the end we raised a
question about the SNLI dataset and the impact on the results, as well as our
concerns about the competition.

本报告是关于在预训练语言模型中应用黑盒调整以进行 few-shot 学习的研究。 我们提出了基于 LMaaS 场景的解决方案，包括多标签词、P0 选择、滚动更新策略、MLP 分类器的多任务损失以及使用集成方法进一步提高广义化能力。 最后，我们提出了有关 SNLI 数据集对结果影响的问题，以及我们对比赛的担忧。