English
Related papers

Related papers: Stubborn Lexical Bias in Data and Models

200 papers

Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for predictions.…

Machine Learning · Computer Science 2025-05-22 Xiaoling Zhou , Wei Ye , Rui Xie , Shikun Zhang

Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative'' labels, which occur when some classes are more likely to be labeled…

Machine Learning · Statistics 2023-02-16 Aude Sportisse , Hugo Schmutz , Olivier Humbert , Charles Bouveyron , Pierre-Alexandre Mattei

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this…

Machine Learning · Computer Science 2020-08-17 Megha Srivastava , Tatsunori Hashimoto , Percy Liang

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Amar Kumar , Nima Fathi , Raghav Mehta , Brennan Nichyporuk , Jean-Pierre R. Falet , Sotirios Tsaftaris , Tal Arbel

Spurious bias, a tendency to exploit spurious correlations between superficial input attributes and prediction targets, has revealed a severe robustness pitfall in classical machine learning problems. Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Wenqian Ye , Bohan Liu , Guangtao Zheng , Di Wang , Yunsheng Ma , Xu Cao , Bolin Lai , James M. Rehg , Aidong Zhang

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…

Machine Learning · Computer Science 2020-12-09 Yining Chen , Colin Wei , Ananya Kumar , Tengyu Ma

Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of…

Computation and Language · Computer Science 2025-06-18 Erik Derner , Sara Sansalvador de la Fuente , Yoan Gutiérrez , Paloma Moreda , Nuria Oliver

Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood. Much of the research on data augmentation (DA) has focused on improving existing…

Machine Learning · Computer Science 2023-04-13 Damien A. Dablain , Nitesh V. Chawla

Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and…

Computation and Language · Computer Science 2022-12-06 Johannes Mario Meissner , Saku Sugawara , Akiko Aizawa

While existing social bot detectors perform well on benchmarks, their robustness across diverse real-world scenarios remains limited due to unclear ground truth and varied misleading cues. In particular, the impact of shortcut learning,…

Computation and Language · Computer Science 2026-03-24 Shiyan Zheng , Herun Wan , Minnan Luo , Junhang Huang

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…

Machine Learning · Computer Science 2022-04-05 Seonguk Seo , Joon-Young Lee , Bohyung Han

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…

Computation and Language · Computer Science 2024-02-06 Oscar Chew , Hsuan-Tien Lin , Kai-Wei Chang , Kuan-Hao Huang

The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data. For example, a classifier may misclassify dog breeds based on the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Aengus Lynch , Gbètondji J-S Dovonon , Jean Kaddour , Ricardo Silva

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

Computation and Language · Computer Science 2021-09-01 Dimion Asael , Zachary Ziegler , Yonatan Belinkov

Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly…

Machine Learning · Computer Science 2022-01-12 Vishnu Suresh Lokhande , Kihyuk Sohn , Jinsung Yoon , Madeleine Udell , Chen-Yu Lee , Tomas Pfister

Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been…

Computation and Language · Computer Science 2021-02-03 Yadollah Yaghoobzadeh , Soroush Mehri , Remi Tachet , T. J. Hazen , Alessandro Sordoni

Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize this bias and investigate the situations in which it can be…

Machine Learning · Statistics 2021-06-01 Sebastian Farquhar , Yarin Gal , Tom Rainforth

Spurious correlation caused by subgroup underrepresentation has received increasing attention as a source of bias that can be perpetuated by deep neural networks (DNNs). Distributionally robust optimization has shown success in addressing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Nilesh Kumar , Ruby Shrestha , Zhiyuan Li , Linwei Wang

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Computation and Language · Computer Science 2021-09-10 Timo Schick , Sahana Udupa , Hinrich Schütze

In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when…

Machine Learning · Computer Science 2025-02-04 Yuqing Zhou , Ziwei Zhu
‹ Prev 1 3 4 5 6 7 10 Next ›