A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such methods to commonsense reasoning tasks faces two unique challenges, i.e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever. In this paper, we systematically investigate how to leverage commonsense knowledge retrieval to improve commonsense reasoning tasks. We proposed a unified framework of retrieval-augmented commonsense reasoning (called RACo), including a newly constructed commonsense corpus with over 20 million documents and novel strategies for training a commonsense retriever. We conducted experiments on four different commonsense reasoning tasks. Extensive evaluation results showed that our proposed RACo can significantly outperform other knowledge-enhanced method counterparts, achieving new SoTA performance on the CommonGen and CREAK leaderboards.
@article{arxiv.2210.12887,
title = {Retrieval Augmentation for Commonsense Reasoning: A Unified Approach},
author = {Wenhao Yu and Chenguang Zhu and Zhihan Zhang and Shuohang Wang and Zhuosheng Zhang and Yuwei Fang and Meng Jiang},
journal= {arXiv preprint arXiv:2210.12887},
year = {2022}
}