相关论文: Leveraging Prototypical Representations for Mitiga…

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been…

Approaches for mitigating bias in supervised models are designed to reduce models' dependence on specific sensitive features of the input data, e.g., mentioned social groups. However, in the case of hate speech detection, it is not always…

Fair machine learning has become a significant research topic with broad societal impact. However, most fair learning methods require direct access to personal demographic data, which is increasingly restricted to use for protecting user…

Recent evaluations of Large language models (LLMs) audit social bias primarily through prompts that explicitly reference demographic attributes, overlooking whether models infer sensitive demographics from neutral questions. Such inference…

The increasing utilization of large language models raises significant concerns about the propagation of social biases, which may result in harmful and unfair outcomes. However, existing debiasing methods treat the biased and unbiased…

The research of open-domain dialog systems has been greatly prospered by neural models trained on large-scale corpora, however, such corpora often introduce various safety problems (e.g., offensive languages, biases, and toxic behaviors)…

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…

Introduction: Healthcare AI models often inherit biases from their training data. While efforts have primarily targeted bias in structured data, mental health heavily depends on unstructured data. This study aims to detect and mitigate…

The increasing amount of applications of Artificial Intelligence (AI) has led researchers to study the social impact of these technologies and evaluate their fairness. Unfortunately, current fairness metrics are hard to apply in multi-class…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models…

Machine Learning (ML) models are widely employed to drive many modern data systems. While they are undeniably powerful tools, ML models often demonstrate imbalanced performance and unfair behaviors. The root of this problem often lies in…

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

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…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Visual language models (VLMs) have shown remarkable capabilities in multimodal tasks but face challenges in maintaining fairness across demographic groups, particularly when deployed in federated learning (FL) environments. This paper…

In uses of pre-trained machine learning models, it is a known issue that the target population in which the model is being deployed may not have been reflected in the source population with which the model was trained. This can result in a…