research
∙
08/30/2023
Is the U.S. Legal System Ready for AI's Challenges to Human Values?
Our interdisciplinary study investigates how effectively U.S. laws confr...
share
research
∙
07/07/2023
Evaluating Biased Attitude Associations of Language Models in an Intersectional Context
Language models are trained on large-scale corpora that embed implicit b...
research
∙
06/08/2023
Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks
The rapid deployment of artificial intelligence (AI) models demands a th...
research
∙
05/17/2023
ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages
In this multicultural age, language translation is one of the most perfo...
research
∙
12/21/2022
Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
Nine language-vision AI models trained on web scrapes with the Contrasti...
research
∙
11/07/2022
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Machine learning models are now able to convert user-written text descri...
research
∙
07/01/2022
American == White in Multimodal Language-and-Image AI
Three state-of-the-art language-and-image AI models, CLIP, SLIP, and BLI...
research
∙
06/07/2022
Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics
The statistical regularities in language corpora encode well-known socia...
research
∙
06/03/2022
Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals
Does the grammatical gender of a language interfere when measuring the s...
research
∙
05/23/2022
Markedness in Visual Semantic AI
We evaluate the state-of-the-art multimodal "visual semantic" model CLIP...
research
∙
05/22/2022
Evidence for Hypodescent in Visual Semantic AI
We examine the state-of-the-art multimodal "visual semantic" model CLIP ...
research
∙
03/14/2022
Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
We examine the effects of contrastive visual semantic pretraining by com...
research
∙
03/14/2022
VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluat...
research
∙
10/01/2021
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
We use a dataset of U.S. first names with labels based on predominant ge...
research
∙
10/28/2020
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Recent advances in machine learning leverage massive datasets of unlabel...
research
∙
06/08/2020
Iterative Effect-Size Bias in Ridehailing: Measuring Social Bias in Dynamic Pricing of 100 Million Rides
Algorithmic bias is the systematic preferential or discriminatory treatm...
research
∙
06/06/2020
Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases
With the starting point that implicit human biases are reflected in the ...
research
∙
06/06/2020
ValNorm: A New Word Embedding Intrinsic Evaluation Method Reveals Valence Biases are Consistent Across Languages and Over Decades
Word embeddings learn implicit biases from linguistic regularities captu...
research
∙
04/18/2020
Pro-Russian Biases in Anti-Chinese Tweets about the Novel Coronavirus
The recent COVID-19 pandemic, which was first detected in Wuhan, China, ...
research
∙
02/13/2020
Machines Learn Appearance Bias in Face Recognition
We seek to determine whether state-of-the-art, black box face recognitio...
research
∙
08/25/2016