Human-like biases and undesired social stereotypes exist in large pretrained language
models. Given the wide adoption of these models in real-world applications, mitigating such …

Bias in textual data can lead to skewed interpretations and outcomes when the data is used.
These biases could perpetuate stereotypes, discrimination, or other forms of unfair …

Large language models trained on a mixture of NLP tasks that are converted into a text-to-
text format using prompts, can generalize into novel forms of language and handle novel …

In the realm of digital information, ensuring the fairness and neutrality of textual content,
especially news, is paramount. This paper introduces FairFrame, a novel framework …

Textual label names (descriptions) are typically semantically rich in many natural language
understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which …

Recent research has revealed that deep neural networks often take dataset biases as a
shortcut to make decisions rather than understand tasks, leading to failures in real-world …

Mitigation of gender bias in NLP has a long history tied to debiasing static word
embeddings. More recently, attention has shifted to debiasing pre-trained language models …