# Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation

arXiv: https://arxiv.org/abs/2205.12593 · HTML: https://mlsanity.com/paper/2205.12593/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 30 of 36)

- [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)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [Towards Debiasing Fact Verification Models](https://mlsanity.com/paper/1908.05267/) (2019)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [Towards Debiasing NLU Models from Unknown Biases](https://mlsanity.com/paper/2009.12303/) (2020)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [Competency Problems: On Finding and Removing Artifacts in Language Data](https://mlsanity.com/paper/2104.08646/) (2021)
- [How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks](https://mlsanity.com/paper/1808.04926/) (2018)
- [Reevaluating Adversarial Examples in Natural Language](https://mlsanity.com/paper/2004.14174/) (2020)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets](https://mlsanity.com/paper/1904.02668/) (2019)
- [Why Machine Reading Comprehension Models Learn Shortcuts?](https://mlsanity.com/paper/2106.01024/) (2021)
- [Attention-over-Attention Neural Networks for Reading Comprehension](https://mlsanity.com/paper/1607.04423/) (2016)

## Built on by (most cited first, 13 of 13)

- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak](https://mlsanity.com/paper/2312.04127/) (2023)
- [Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models](https://mlsanity.com/paper/2409.17455/) (2024)
- [SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2305.11615/) (2023)
- [Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection](https://mlsanity.com/paper/2505.20209/) (2025)
- [BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors](https://mlsanity.com/paper/2503.17717/) (2025)
- [SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases](https://mlsanity.com/paper/2302.14413/) (2023)
- [GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue](https://mlsanity.com/paper/2309.04162/) (2023)
- [Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making](https://mlsanity.com/paper/2310.13610/) (2023)
- [CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models](https://mlsanity.com/paper/2509.05230/) (2025)
- [Rank-Constrained Adaptation for Reliable Real-World Performance](https://mlsanity.com/paper/2602.06924/) (2026)
- [Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation](https://mlsanity.com/paper/2604.12277/) (2026)
- [Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning](https://mlsanity.com/paper/2605.09270/) (2026)

## Abstract (arXiv)

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution of training data. In particular, we define the word highly co-occurring with a specific label as biased word, and the example containing biased word as biased example. Our analysis shows that biased examples are easier for models to learn, while at the time of prediction, biased words make a significantly higher contribution to the models' predictions, and models tend to assign predicted labels over-relying on the spurious correlation between words and labels. To mitigate models' over-reliance on the shortcut (i.e. spurious correlation), we propose a training strategy Less-Learn-Shortcut (LLS): our strategy quantifies the biased degree of the biased examples and down-weights them accordingly. Experimental results on Question Matching, Natural Language Inference and Sentiment Analysis tasks show that LLS is a task-agnostic strategy and can improve the model performance on adversarial data while maintaining good performance on in-domain data.