MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning

Yongfeng Huang, Yanyang Li, Yichong Xu, Lin Zhang, Ruyi Gan, Jiaxing Zhang, Liwei Wang


Abstract
Recent advances in pre-trained language models (PLMs) have facilitated the development ofcommonsense reasoning tasks. However, existing methods rely on multi-hop knowledgeretrieval and thus suffer low accuracy due toembedded noise in the acquired knowledge. In addition, these methods often attain highcomputational costs and nontrivial knowledgeloss because they encode the knowledge independently of the PLM, making it less relevant to the task and thus resulting in a poorlocal optimum. In this work, we propose MultiView Knowledge Retrieval with Prompt Tuning (MVP-Tuning). MVP-Tuning leveragessimilar question-answer pairs in the training setto improve knowledge retrieval and employsa single prompt-tuned PLM to model knowledge and input text jointly. We conduct our experiments on five commonsense reasoning QAbenchmarks to show that MVP-Tuning outperforms all other baselines in 4 out of 5 datasetswith less than 2% trainable parameters. MVPTuning even gets a new state-of-the-art resulton OpenBookQA and is number one on theleaderboard.
Anthology ID:
2023.acl-long.750
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13417–13432
Language:
URL:
https://aclanthology.org/2023.acl-long.750
DOI:
10.18653/v1/2023.acl-long.750
Bibkey:
Cite (ACL):
Yongfeng Huang, Yanyang Li, Yichong Xu, Lin Zhang, Ruyi Gan, Jiaxing Zhang, and Liwei Wang. 2023. MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13417–13432, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning (Huang et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.750.pdf
Video:
 https://aclanthology.org/2023.acl-long.750.mp4