Bias Detection

60 papers with code • 5 benchmarks • 8 datasets

Bias detection is the task of detecting and measuring racism, sexism and otherwise discriminatory behavior in a model (Source:

Most implemented papers

Automated Dependence Plots

davidinouye/adp 2 Dec 2019

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.

StereoSet: Measuring stereotypical bias in pretrained language models

moinnadeem/StereoSet ACL 2021

Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases.

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

weiguowilliam/CEAT 6 Jun 2020

Furthermore, we develop two methods, Intersectional Bias Detection (IBD) and Emergent Intersectional Bias Detection (EIBD), to automatically identify the intersectional biases and emergent intersectional biases from static word embeddings in addition to measuring them in contextualized word embeddings.

Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets

tosingithub/bipol 28 Jan 2023

Hence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it.

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor

robvanderg/w2v 23 May 2019

However, beside the intrinsic problems with the analogy task as a bias detection tool, in this paper we show that a series of issues related to how analogies have been implemented and used might have yielded a distorted picture of bias in word embeddings.

Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories

alfredomg/GeBNLP2019 WS 2019

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.

Multilingual sentence-level bias detection in Wikipedia

crim-ca/wiki-bias RANLP 2019

We propose a multilingual method for the extraction of biased sentences from Wikipedia, and use it to create corpora in Bulgarian, French and English.

Predicting the Leading Political Ideology of YouTube Channels Using Acoustic, Textual, and Metadata Information

yoandinkov/interspeech-2019 20 Oct 2019

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.

My Approach = Your Apparatus? Entropy-Based Topic Modeling on Multiple Domain-Specific Text Collections

julian-risch/JCDL2018 25 Nov 2019

Comparative text mining extends from genre analysis and political bias detection to the revelation of cultural and geographic differences, through to the search for prior art across patents and scientific papers.