English
Related papers

Related papers: MABEL: Attenuating Gender Bias using Textual Entai…

200 papers

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Na Min An , Yoonna Jang , Yusuke Hirota , Ryo Hachiuma , Isabelle Augenstein , Hyunjung Shim

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be…

Computation and Language · Computer Science 2022-05-17 Xudong Han , Timothy Baldwin , Trevor Cohn

We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists only a weak correlation between these two types of…

Computation and Language · Computer Science 2022-10-07 Masahiro Kaneko , Danushka Bollegala , Naoaki Okazaki

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective…

Computation and Language · Computer Science 2024-12-17 Tao Zhang , Ziqian Zeng , Yuxiang Xiao , Huiping Zhuang , Cen Chen , James Foulds , Shimei Pan

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Yunfan Yang , Chaoquan Jiang , Zhiyu Lin , Jinlin Xiao , Jiaming Zhang , Jitao Sang

Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they are trained on, while not generalising to different task…

Computation and Language · Computer Science 2022-03-25 Yuxiang Wu , Matt Gardner , Pontus Stenetorp , Pradeep Dasigi

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Computation and Language · Computer Science 2024-10-21 Thomas Uriot

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

Computation and Language · Computer Science 2025-07-02 Kang He , Yuzhe Ding , Haining Wang , Fei Li , Chong Teng , Donghong Ji

Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these…

Computation and Language · Computer Science 2020-10-27 Vaibhav Kumar , Tenzin Singhay Bhotia , Vaibhav Kumar

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Computation and Language · Computer Science 2025-03-12 Gleb Kuzmin , Neemesh Yadav , Ivan Smirnov , Timothy Baldwin , Artem Shelmanov

Vision-language models (VLMs) pre-trained on extensive datasets can inadvertently learn biases by correlating gender information with specific objects or scenarios. Current methods, which focus on modifying inputs and monitoring changes in…

Artificial Intelligence · Computer Science 2025-06-09 Zhaotian Weng , Zijun Gao , Jerone Andrews , Jieyu Zhao

Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases. However, most of the works address a…

Computation and Language · Computer Science 2024-02-13 Prachi Jain , Ashutosh Sathe , Varun Gumma , Kabir Ahuja , Sunayana Sitaram

The use of language models (LMs) has increased considerably in recent years, and the biases and stereotypes in training data that are reflected in the LM outputs are causing social problems. In this paper, inspired by the task arithmetic,…

Computation and Language · Computer Science 2024-12-17 Daiki Shirafuji , Makoto Takenaka , Shinya Taguchi

Model-based evaluation metrics (e.g., CLIPScore and GPTScore) have demonstrated decent correlations with human judgments in various language generation tasks. However, their impact on fairness remains largely unexplored. It is widely…

Computation and Language · Computer Science 2023-11-06 Haoyi Qiu , Zi-Yi Dou , Tianlu Wang , Asli Celikyilmaz , Nanyun Peng

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

Computation and Language · Computer Science 2024-08-09 Vipul Gupta , Pranav Narayanan Venkit , Hugo Laurençon , Shomir Wilson , Rebecca J. Passonneau

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Olga Russakovsky

Bias in machine learning models can lead to unfair decision making, and while it has been well-studied in the image and text domains, it remains underexplored in action recognition. Action recognition models often suffer from background…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Joseph Fioresi , Ishan Rajendrakumar Dave , Mubarak Shah

Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has predominantly focused on mitigating discriminative bias in the…

Machine Learning · Computer Science 2024-06-19 Zhining Liu , Ruizhong Qiu , Zhichen Zeng , Yada Zhu , Hendrik Hamann , Hanghang Tong

Bolukbasi et al. (2016) presents one of the first gender bias mitigation techniques for word representations. Their method takes pre-trained word representations as input and attempts to isolate a linear subspace that captures most of the…

Machine Learning · Computer Science 2024-05-24 Francisco Vargas , Ryan Cotterell