English
Related papers

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

200 papers

A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…

Computation and Language · Computer Science 2026-02-11 Shweta Parihar , Liu Guangliang , Natalie Parde , Lu Cheng

Despite the evolution of language models, they continue to portray harmful societal biases and stereotypes inadvertently learned from training data. These inherent biases often result in detrimental effects in various applications.…

Computation and Language · Computer Science 2024-07-24 Ewoenam Kwaku Tokpo , Toon Calders

This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA),…

Computation and Language · Computer Science 2020-02-06 Rowan Hall Maudslay , Hila Gonen , Ryan Cotterell , Simone Teufel

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

Computation and Language · Computer Science 2023-05-24 Ananth Balashankar , Xuezhi Wang , Yao Qin , Ben Packer , Nithum Thain , Jilin Chen , Ed H. Chi , Alex Beutel

Counterfactual data augmentation (CDA) is a method for controlling information or biases in training datasets by generating a complementary dataset with typically opposing biases. Prior work often either relies on hand-crafted rules or…

Machine Learning · Computer Science 2025-02-26 Mitchell Plyler , Min Chi

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

Computation and Language · Computer Science 2019-06-03 Kaiji Lu , Piotr Mardziel , Fangjing Wu , Preetam Amancharla , Anupam Datta

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on…

Computation and Language · Computer Science 2022-11-02 Tanay Dixit , Bhargavi Paranjape , Hannaneh Hajishirzi , Luke Zettlemoyer

Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited with promoting core features of the construct over spurious artifacts that happen to…

Computation and Language · Computer Science 2022-05-10 Indira Sen , Mattia Samory , Claudia Wagner , Isabelle Augenstein

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

Machine Learning · Computer Science 2023-11-22 Abbavaram Gowtham Reddy , Saketh Bachu , Saloni Dash , Charchit Sharma , Amit Sharma , Vineeth N Balasubramanian

Rationales, snippets of extracted text that explain an inference, have emerged as a popular framework for interpretable natural language processing (NLP). Rationale models typically consist of two cooperating modules: a selector and a…

Computation and Language · Computer Science 2022-01-17 Mitchell Plyler , Michael Green , Min Chi

The increasingly large size of modern pretrained language models not only makes them inherit more human-like biases from the training corpora, but also makes it computationally expensive to mitigate such biases. In this paper, we…

Computation and Language · Computer Science 2023-06-08 Zhongbin Xie , Thomas Lukasiewicz

In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage. Over time, new models must be trained as new training examples and features become available. However, feedback loops…

Machine Learning · Computer Science 2023-11-01 Victoria Lin , Louis-Philippe Morency , Dimitrios Dimitriadis , Srinagesh Sharma

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where…

Computation and Language · Computer Science 2023-02-14 Zhongbin Xie , Vid Kocijan , Thomas Lukasiewicz , Oana-Maria Camburu

Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English counterfactuals and…

Computation and Language · Computer Science 2026-04-07 Qianli Wang , Van Bach Nguyen , Yihong Liu , Fedor Splitt , Nils Feldhus , Christin Seifert , Hinrich Schütze , Sebastian Möller , Vera Schmitt

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Computation and Language · Computer Science 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Kirill Sirotkin , Marcos Escudero-Viñolo , Pablo Carballeira , Mayug Maniparambil , Catarina Barata , Noel E. O'Connor

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other…

Computation and Language · Computer Science 2022-11-28 Abdelrahman Zayed , Prasanna Parthasarathi , Goncalo Mordido , Hamid Palangi , Samira Shabanian , Sarath Chandar

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Counterfactual data…

Computation and Language · Computer Science 2024-04-02 Hannah Chen , Yangfeng Ji , David Evans

Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve…

Computation and Language · Computer Science 2025-02-03 Tomasz Limisiewicz , David Mareček , Tomáš Musil

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However,…

Machine Learning · Computer Science 2025-07-11 Xiaoling Zhou , Ou Wu , Michael K. Ng
‹ Prev 1 2 3 10 Next ›