# Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis

arXiv: https://arxiv.org/abs/2305.13654 · HTML: https://mlsanity.com/paper/2305.13654/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://mlsanity.com/paper/1909.06321/) (2019)
- [Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual](https://mlsanity.com/paper/1908.10763/) (2019)
- [Towards Debiasing NLU Models from Unknown Biases](https://mlsanity.com/paper/2009.12303/) (2020)
- [Competency Problems: On Finding and Removing Artifacts in Language Data](https://mlsanity.com/paper/2104.08646/) (2021)
- [Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance](https://mlsanity.com/paper/2005.00315/) (2020)
- [Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models](https://mlsanity.com/paper/2110.07736/) (2021)
- [Examining and Combating Spurious Features under Distribution Shift](https://mlsanity.com/paper/2106.07171/) (2021)
- [Identifying Spurious Correlations for Robust Text Classification](https://mlsanity.com/paper/2010.02458/) (2020)
- [Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles](https://mlsanity.com/paper/2011.03856/) (2020)
- [Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens](https://mlsanity.com/paper/2210.14011/) (2022)
- [Explanation-based Finetuning Makes Models More Robust to Spurious Cues](https://mlsanity.com/paper/2305.04990/) (2023)
- [MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain](https://mlsanity.com/paper/2106.01491/) (2021)
- [FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding](https://mlsanity.com/paper/2109.12742/) (2021)
- [Finding Dataset Shortcuts with Grammar Induction](https://mlsanity.com/paper/2210.11560/) (2022)

## Built on by (most cited first, 11 of 11)

- [Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks](https://mlsanity.com/paper/2408.15721/) (2024)
- [Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models](https://mlsanity.com/paper/2409.17455/) (2024)
- [Focus On This, Not That! Steering LLMs with Adaptive Feature Specification](https://mlsanity.com/paper/2410.22944/) (2024)
- [Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods](https://mlsanity.com/paper/2510.26038/) (2025)
- [Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security](https://mlsanity.com/paper/2511.16229/) (2025)
- [CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples](https://mlsanity.com/paper/2508.21083/) (2025)
- [Generalizing to Unseen Disaster Events: A Causal View](https://mlsanity.com/paper/2511.10120/) (2025)
- [Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation](https://mlsanity.com/paper/2602.20400/) (2026)
- [Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation](https://mlsanity.com/paper/2604.12277/) (2026)
- [X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis](https://mlsanity.com/paper/2608.24563/) (2026)
- [QTrans: A Quantum Transformer for Sentiment Classification](https://mlsanity.com/paper/2609.12011/) (2026)

## Abstract (arXiv)

Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classifier may erroneously learn that the token "performances" is commonly associated with positive movie reviews. Relying on these spurious correlations degrades the classifiers performance when it deploys on out-of-distribution data. In this paper, we examine the implications of spurious correlations through a novel perspective called neighborhood analysis. The analysis uncovers how spurious correlations lead unrelated words to erroneously cluster together in the embedding space. Driven by the analysis, we design a metric to detect spurious tokens and also propose a family of regularization methods, NFL (doN't Forget your Language) to mitigate spurious correlations in text classification. Experiments show that NFL can effectively prevent erroneous clusters and significantly improve the robustness of classifiers without auxiliary data. The code is publicly available at https://github.com/oscarchew/doNt-Forget-your-Language.