English
Related papers

Related papers: Model-based Counterfactual Generator for Gender Bi…

200 papers

Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping,…

Computation and Language · Computer Science 2025-08-28 Qianli Wang , Van Bach Nguyen , Nils Feldhus , Luis Felipe Villa-Arenas , Christin Seifert , Sebastian Möller , Vera Schmitt

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Computation and Language · Computer Science 2018-08-23 Ji Ho Park , Jamin Shin , Pascale Fung

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…

Computation and Language · Computer Science 2023-05-19 Chantal Amrhein , Florian Schottmann , Rico Sennrich , Samuel Läubli

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Long Chen , Yuhang Zheng , Jun Xiao

The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare. In this work, we propose to use counterfactual data…

Machine Learning · Computer Science 2024-01-10 Amir Feder , Yoav Wald , Claudia Shi , Suchi Saria , David Blei

Deep learning models often learn and exploit spurious correlations in training data, using these non-target features to inform their predictions. Such reliance leads to performance degradation and poor generalization on unseen data. To…

Computation and Language · Computer Science 2025-11-21 Kyohoon Jin , Juhwan Choi , Jungmin Yun , Junho Lee , Soojin Jang , Youngbin Kim

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…

Computation and Language · Computer Science 2026-03-05 Anirudh Bharadwaj , Chaitanya Malaviya , Nitish Joshi , Mark Yatskar

Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text modalities. In this work, we dissect the contributions of…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Vivek Hruday Kavuri , Vysishtya Karanam , Venkata Jahnavi Venkamsetty , Kriti Madumadukala , Lakshmipathi Balaji Darur , Ponnurangam Kumaraguru

The class imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the number of samples is one way to…

Computation and Language · Computer Science 2023-06-02 Akbar Karimi , Lucie Flek

Data augmentation has been shown to effectively improve the performance of multimodal machine learning models. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities.…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Zixu Wang , Yishu Miao , Lucia Specia

While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using…

Computation and Language · Computer Science 2022-03-17 Nitish Joshi , He He

Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires the identification of the disentangled latent…

Machine Learning · Computer Science 2024-02-26 Hanqi Yan , Lingjing Kong , Lin Gui , Yuejie Chi , Eric Xing , Yulan He , Kun Zhang

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

Computation and Language · Computer Science 2021-09-09 Víctor M. Sánchez-Cartagena , Miquel Esplà-Gomis , Juan Antonio Pérez-Ortiz , Felipe Sánchez-Martínez

The detection of sexism in online content remains an open problem, as harmful language disproportionately affects women and marginalized groups. While automated systems for sexism detection have been developed, they still face two key…

Computation and Language · Computer Science 2025-06-09 Sahrish Khan , Arshad Jhumka , Gabriele Pergola

Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data…

Computation and Language · Computer Science 2023-10-24 Yingjie Zhu , Jiasheng Si , Yibo Zhao , Haiyang Zhu , Deyu Zhou , Yulan He

VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language. Recent debiasing methods proposed to exclude the language prior during inference.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Yulei Niu , Kaihua Tang , Hanwang Zhang , Zhiwu Lu , Xian-Sheng Hua , Ji-Rong Wen

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Machine Learning · Computer Science 2021-06-07 Robert-Florian Samoilescu , Arnaud Van Looveren , Janis Klaise

Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically training a surrogate model…

Machine Learning · Computer Science 2024-11-13 Pasan Dissanayake , Sanghamitra Dutta

In this paper we show that GEC systems display gender bias related to the use of masculine and feminine terms and the gender-neutral singular "they". We develop parallel datasets of texts with masculine and feminine terms and singular…

Computation and Language · Computer Science 2023-06-14 Gunnar Lund , Kostiantyn Omelianchuk , Igor Samokhin

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Abhishek Sinha , Kumar Ayush , Jiaming Song , Burak Uzkent , Hongxia Jin , Stefano Ermon