# Improved Text Classification via Test-Time Augmentation

arXiv: https://arxiv.org/abs/2206.13607 · HTML: https://mlsanity.com/paper/2206.13607/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples](https://mlsanity.com/paper/1710.10766/) (2017)
- [Understanding Measures of Uncertainty for Adversarial Example Detection](https://mlsanity.com/paper/1803.08533/) (2018)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [Better Aggregation in Test-Time Augmentation](https://mlsanity.com/paper/2011.11156/) (2020)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [An Analysis of Simple Data Augmentation for Named Entity Recognition](https://mlsanity.com/paper/2010.11683/) (2020)
- [Deflecting Adversarial Attacks with Pixel Deflection](https://mlsanity.com/paper/1801.08926/) (2018)
- [Generalized Data Augmentation for Low-Resource Translation](https://mlsanity.com/paper/1906.03785/) (2019)
- [XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering](https://mlsanity.com/paper/1905.11471/) (2019)
- [Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble](https://mlsanity.com/paper/1703.03108/) (2017)
- [An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering](https://mlsanity.com/paper/1912.02145/) (2019)
- [Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering](https://mlsanity.com/paper/1904.06652/) (2019)
- [Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting](https://mlsanity.com/paper/1909.06002/) (2019)
- [Transforming Wikipedia into Augmented Data for Query-Focused Summarization](https://mlsanity.com/paper/1911.03324/) (2019)
- [Controllable Data Synthesis Method for Grammatical Error Correction](https://mlsanity.com/paper/1909.13302/) (2019)

## Built on by (most cited first, 7 of 7)

- [Online Continual Learning for Robust Indoor Object Recognition](https://mlsanity.com/paper/2307.09827/) (2023)
- [Improving Black-box Robustness with In-Context Rewriting](https://mlsanity.com/paper/2402.08225/) (2024)
- [Addressing Distribution Shift at Test Time in Pre-trained Language Models](https://mlsanity.com/paper/2212.02384/) (2022)
- [Test-time augmentation improves efficiency in conformal prediction](https://mlsanity.com/paper/2505.22764/) (2025)
- [UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Posts](https://mlsanity.com/paper/2304.04539/) (2023)
- [Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute](https://mlsanity.com/paper/2608.09351/) (2026)
- [GATTA: Graph Active Learning with Test-Time Augmentation](https://mlsanity.com/paper/2608.15084/) (2026)

## Abstract (arXiv)

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.