Нәсілдік бейімділік

AbstractSports broadcasters inject drama into play-by-play commentary by building team and player narratives through subjective analyses and anecdotes. Prior studies based on small datasets and manual coding show that such …...

AbstractWe investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected …...

AbstractHuman-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 biases has become an emerging and …...

AbstractModels trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., …...