# Pretrained Transformers Do not Always Improve Robustness

arXiv: https://arxiv.org/abs/2210.07663 · HTML: https://mlsanity.com/paper/2210.07663/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Pretrained Transformers Improve Out-of-Distribution Robustness](https://mlsanity.com/paper/2004.06100/) (2020)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [Towards Universal Paraphrastic Sentence Embeddings](https://mlsanity.com/paper/1511.08198/) (2015)
- [DQI: Measuring Data Quality in NLP](https://mlsanity.com/paper/2005.00816/) (2020)
- [How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation](https://mlsanity.com/paper/2106.05532/) (2021)
- [Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness](https://mlsanity.com/paper/2203.07653/) (2022)
- [Our Evaluation Metric Needs an Update to Encourage Generalization](https://mlsanity.com/paper/2007.06898/) (2020)

## Built on by (most cited first, 2 of 2)

- [Adventures of Trustworthy Vision-Language Models: A Survey](https://mlsanity.com/paper/2312.04231/) (2023)
- [Reasoning Bias of Next Token Prediction Training](https://mlsanity.com/paper/2502.02007/) (2025)

## Abstract (arXiv)

Pretrained Transformers (PT) have been shown to improve Out of Distribution (OOD) robustness than traditional models such as Bag of Words (BOW), LSTMs, Convolutional Neural Networks (CNN) powered by Word2Vec and Glove embeddings. How does the robustness comparison hold in a real world setting where some part of the dataset can be noisy? Do PT also provide more robust representation than traditional models on exposure to noisy data? We perform a comparative study on 10 models and find an empirical evidence that PT provide less robust representation than traditional models on exposure to noisy data. We investigate further and augment PT with an adversarial filtering (AF) mechanism that has been shown to improve OOD generalization. However, increase in generalization does not necessarily increase robustness, as we find that noisy data fools the AF method powered by PT.