2.9k citations · 3.9k across the 22 of their papers we have counts for
22 papers
Is the U.S. Legal System Ready for AI's Challenges to Human Values?
Inyoung Cheong, Aylin Caliskan, Tadayoshi Kohno
Our interdisciplinary study investigates how effectively U.S. laws confront the challenges posed by Generative AI to human values. Through an analysis of diverse hypothetical scena…
Evaluating Biased Attitude Associations of Language Models in an Intersectional Context
Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
Language models are trained on large-scale corpora that embed implicit biases documented in psychology. Valence associations (pleasantness/unpleasantness) of social groups determin…
Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks
Katelyn X. Mei, Sonia Fereidooni, Aylin Caliskan
The rapid deployment of artificial intelligence (AI) models demands a thorough investigation of biases and risks inherent in these models to understand their impact on individuals…
Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
Robert Wolfe, Yiwei Yang, Bill Howe +1
Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists…
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Federico Bianchi, Pratyusha Kalluri, Esin Durmus +7
Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day.…
American == White in Multimodal Language-and-Image AI
Robert Wolfe, Aylin Caliskan
Three state-of-the-art language-and-image AI models, CLIP, SLIP, and BLIP, are evaluated for evidence of a bias previously observed in social and experimental psychology: equating…
Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics
Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth +2
The statistical regularities in language corpora encode well-known social biases into word embeddings. Here, we focus on gender to provide a comprehensive analysis of group-based b…
Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals
Shiva Omrani Sabbaghi, Aylin Caliskan
Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements i…
Markedness in Visual Semantic AI
Robert Wolfe, Aylin Caliskan
We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or et…
Evidence for Hypodescent in Visual Semantic AI
Robert Wolfe, Mahzarin R. Banaji, Aylin Caliskan
We examine the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for the rule of hypodescent, or one-drop rule, whereby multiracia…
Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
Robert Wolfe, Aylin Caliskan
We examine the effects of contrastive visual semantic pretraining by comparing the geometry and semantic properties of contextualized English language representations formed by GPT…
VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
Robert Wolfe, Aylin Caliskan
VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings (CWEs). VAST uses valence, the association of a word with pleasa…
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
Robert Wolfe, Aylin Caliskan
We use a dataset of U.S. first names with labels based on predominant gender and racial group to examine the effect of training corpus frequency on tokenization, contextualization,…
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Ryan Steed, Aylin Caliskan
Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to…
Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms
Akshat Pandey, Aylin Caliskan
Ridehailing applications that collect mobility data from individuals to inform smart city planning predict each trip's fare pricing with automated algorithms that rely on artificia…
Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases
Wei Guo, Aylin Caliskan
With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. St…
ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries
Autumn Toney-Wails, Aylin Caliskan
Word embeddings learn implicit biases from linguistic regularities captured by word co-occurrence statistics. By extending methods that quantify human-like biases in word embedding…
Automatically Characterizing Targeted Information Operations Through Biases Present in Discourse on Twitter
Autumn Toney, Akshat Pandey, Wei Guo +2
This paper considers the problem of automatically characterizing overall attitudes and biases that may be associated with emerging information operations via artificial intelligenc…
A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild
Ryan Steed, Aylin Caliskan
Research in social psychology has shown that people's biased, subjective judgments about another's personality based solely on their appearance are not predictive of their actual p…
Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments
Edwin Dauber, Aylin Caliskan, Richard Harang +4
Program authorship attribution has implications for the privacy of programmers who wish to contribute code anonymously. While previous work has shown that complete files that are i…
Semantics derived automatically from language corpora contain human-like biases
Aylin Caliskan, Joanna J. Bryson, Arvind Narayanan
Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention…
When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries
Aylin Caliskan, Fabian Yamaguchi, Edwin Dauber +4
The ability to identify authors of computer programs based on their coding style is a direct threat to the privacy and anonymity of programmers. While recent work found that source…