Abstract
Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive experiments demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming the fine-tuned counterpart.- Anthology ID:
- 2023.acl-long.717
- 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:
- 12813–12832
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.717
- DOI:
- 10.18653/v1/2023.acl-long.717
- Cite (ACL):
- Rheeya Uppaal, Junjie Hu, and Yixuan Li. 2023. Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12813–12832, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection (Uppaal et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/landing_page/2023.acl-long.717.pdf