Bias detection is the task of detecting and measuring racism, sexism and otherwise discriminatory behavior in a model (Source: https://stereoset.mit.edu/)
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The package includes a series of methods for bias mitigation that aim to diminish the discrimination in the model.
Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases.
Ranked #1 on Bias Detection on StereoSet
The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data.
We find that some domains are definitely more prone to gender bias than others, and that the categories of gender bias present also vary for each set of word embeddings.
Subjective bias detection is critical for applications like propaganda detection, content recommendation, sentiment analysis, and bias neutralization.
Ranked #1 on Bias Detection on Wiki Neutrality Corpus
To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model.
Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only.
We propose a multilingual method for the extraction of biased sentences from Wikipedia, and use it to create corpora in Bulgarian, French and English.