Pretrained Transformers Improve Out-of-Distribution Robustness
Dan Hendrycks, Xiaoyuan Liu, Eric Wallace, Adam Dziedzic, Rishabh Krishnan, Dawn Song
Abstract
Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for seven NLP datasets by constructing a new robustness benchmark with realistic distribution shifts. We measure the generalization of previous models including bag-of-words models, ConvNets, and LSTMs, and we show that pretrained Transformers’ performance declines are substantially smaller. Pretrained transformers are also more effective at detecting anomalous or OOD examples, while many previous models are frequently worse than chance. We examine which factors affect robustness, finding that larger models are not necessarily more robust, distillation can be harmful, and more diverse pretraining data can enhance robustness. Finally, we show where future work can improve OOD robustness.- Anthology ID:
- 2020.acl-main.244
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2744–2751
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.244
- DOI:
- 10.18653/v1/2020.acl-main.244
- Cite (ACL):
- Dan Hendrycks, Xiaoyuan Liu, Eric Wallace, Adam Dziedzic, Rishabh Krishnan, and Dawn Song. 2020. Pretrained Transformers Improve Out-of-Distribution Robustness. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2744–2751, Online. Association for Computational Linguistics.
- Cite (Informal):
- Pretrained Transformers Improve Out-of-Distribution Robustness (Hendrycks et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.244.pdf
- Code
- camelop/NLP-Robustness
- Data
- IMDb Movie Reviews, MultiNLI, ReCoRD, SNLI, SST, SST-2