activity
20222024
most citedBias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks

52 citations · 65 across the 9 of their papers we have counts for

collaborators

7 papers

cs.CY20244 cited

Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach

Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam +2

Our research investigates the impact of Generative Artificial Intelligence (GAI) models, specifically text-to-image generators (T2Is), on the representation of non-Western cultures…

cs.CY2024

"I don't see myself represented here at all": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities

Sourojit Ghosh, Nina Lutz, Aylin Caliskan

Though research into text-to-image generators (T2Is) such as Stable Diffusion has demonstrated their amplification of societal biases and potentials to cause harm, such research ha…

cs.CY20241 cited

A Taxonomy of Stereotype Content in Large Language Models

Gandalf Nicolas, Aylin Caliskan

This study introduces a taxonomy of stereotype content in contemporary large language models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and widely use…

cs.CL20232 cited

Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition

Isaac Slaughter, Craig Greenberg, Reva Schwartz +1

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this w…

cs.CY20231 cited

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…

cs.CY202352 cited

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…