Bias Detection
Related Papers
Adversarial Removal of Demographic Attributes Revisited
AbstractElazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier …...
In Plain Sight: Media Bias Through the Lens of Factual Reporting
AbstractThe increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection. While prior work in NLP has …...
Context in Informational Bias Detection
AbstractInformational bias is bias conveyed through sentences or clauses that provide tangential, speculative or background information that can sway readers’ opinions towards entities. By nature, informational bias is context-dependent, but …...
Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
AbstractWe present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against …...
Using Social and Linguistic Information to Adapt Pretrained Representations for Political Perspective Identification
Understanding the political perspective shap- ing the way events are discussed in the media is increasingly important due to the dramatic change in news distribution. With the advance in text …...
VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models
AbstractIn this paper we study how to measure stereotypical bias in pre-trained vision-language models. We leverage a recently released text-only dataset, StereoSet, which covers a wide range of stereotypical bias, …...