Abstract / Description of output
In this paper, we introduce and discuss the pervasive issue of bias in the large language models that are currently at the core of mainstream approaches to Natural Language Processing (NLP). We first introduce data selection bias, that is, the bias caused by the choice of texts that make up a training corpus. Then, we survey the different types of social bias evidenced in the text generated by language models trained on such corpora, ranging from gender to age, from sexual orientation to ethnicity, and from religion to culture. We conclude with directions focused on measuring, reducing, and tackling the aforementioned types of bias.
Original language | English |
---|---|
Article number | 10 |
Pages (from-to) | 1-21 |
Journal | Journal of Data and Information Quality |
Volume | 15 |
Issue number | 2 |
DOIs | |
Publication status | Published - 22 Jun 2023 |
Keywords / Materials (for Non-textual outputs)
- bias in NLP
- language models