Pre-trained Language Models (PLMs) have been shown to inherit and even amplify the social biases contained in the training corpus, leading to undesired stereotype in real-world applications. Existing techniques for mitigating the social biases of ...

ChatGPT is rapidly gaining interest and attracts many researchers, practitioners and users due to its availability, potentials and capabilities. Nevertheless, there are several voices and studies that point out the flaws of ChatGPT such as its ...

Warning: This paper contains examples of offensive language, including insulting or objectifying expressions.

Various existing studies have analyzed what social biases are inherited by NLP models. These biases may directly ...

• We conducted research to examine if language models inherit biases toward animals.

Existing methods for debiasing word embeddings often do so only superficially, in that words that are stereotypically associated with, e.g., a particular gender in the original embedding space can still be clustered together in the debiased space. ...

Interactive Voice Systems (IVSs) are automated answering systems with pre-recorded menu options that are navigated by the user with keypresses and vocal responses. These systems are increasing in popularity with many companies because they ...