Abstract
In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast the problem as a stochastic decision-making process, aiming to determine the best adapted model after adaptation. We discuss two frameworks: multi-armed bandit learning and multi-armed dueling bandits. Compared to multi-armed bandit learning, the dueling framework allows pairwise collaboration among K models, which is solved by a novel method named Co-UCB proposed in this work. Experiments on six datasets of extractive question answering (QA) show that the dueling framework using Co-UCB is more effective than other strong baselines for our studied problem.- Anthology ID:
- 2023.acl-long.537
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9647–9660
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.537
- DOI:
- Cite (ACL):
- Hai Ye, Qizhe Xie, and Hwee Tou Ng. 2023. Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9647–9660, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering (Ye et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.acl-long.537.pdf