相关论文: MABEL: Attenuating Gender Bias using Textual Entai…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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,…

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…

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…

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…

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…

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…

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…