Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals

Hagendorff, Thilo; Bossert, Leonie; Fai, Tse Yip; Сингер, Петер

doi:10.48550/arxiv.2202.10848

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A notable exception is the very recent study by Hagendorff et al (2022). They have coonducted research on speciesist biases in image recognition, recommendation systems, and analyzed static word embedding (word2vec (Mikolov et al, 2013), GloVe (Pennington et al, 2014)), GPT-3 (Brown et al, 2020) and Delphi (Jiang et al, 2021) by using specific word lists and template sentences.…”

Section: Social Bias In Language Modelsmentioning

confidence: 99%

Speciesist Language and Nonhuman Animal Bias in English Masked Language Models

Takeshita,

Rzepka,

Araki

2022

Preprint

View full text Add to dashboard Cite

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 or indirectly harm people, therefore previous studies have focused only on human attributes. If the social biases in NLP models can be indirectly harmful to humans involved, then the models can also indirectly harm nonhuman animals. However, until recently no research on social biases in NLP regarding nonhumans existed. In this paper 1 , we analyze biases to nonhuman animals, i.e. speciesist bias, inherent in English Masked Language Models. We analyze this bias using template-based and corpus-extracted sentences which contain speciesist (or non-speciesist) language, to show that these models tend to associate harmful words with nonhuman animals. Our code for reproducing the experiments will be made available on GitHub 2 .1 Anonymous previous version of this paper is accessible at https://openreview.net/forum?id=dfqMpjZOgv4, we have also published a paper on this topic in Japanese (Takeshita et al.

show abstract

Section: Social Bias In Language Modelsmentioning

confidence: 99%