Abstract: Recent advances in pre-trained language models (PLMs) have facilitated the development of commonsense reasoning tasks. However, existing methods rely on multi-hop knowledge retrieval and thus suffer low accuracy due to embedded noise in the acquired knowledge. In addition, these methods often attain high computational costs and nontrivial knowledge loss because they encode the knowledge independently of the PLM, making it less relevant to the task and thus resulting in a poor local optimum. In this work, we propose MultiView Knowledge Retrieval with Prompt Tuning (MVP-Tuning). MVP-Tuning leverages similar question-answer pairs in the training set to improve knowledge retrieval and employs a single prompt-tuned PLM to model knowledge and input text jointly. We conduct our experiments on five commonsense reasoning QA benchmarks to show that MVP-Tuning outperforms all other baselines in 4 out of 5 datasets with less than 2\% trainable parameters. MVPTuning even gets a new state-of-the-art result on OpenBookQA and is number one on the leaderboard.