Aylin Caliskan

My first name is pronounced as Eye-lin

Assistant Professor
The Information School
Paul G. Allen School of Computer Science & Engineering (courtesy) Co-director • Tech Policy Lab
Faculty Affiliate • UW NLP RAISE, VSD Lab
University of Washington

Nonresident Fellow in Governance at Brookings
  aylin@uw.edu        @aylin_cim

Aylin

I have formal training in computer science, information systems, and robotics. My research interests lie in artificial intelligence (AI) ethics, AI bias, natural language processing, multimodal machine learning, and human-AI interaction. Bias and ethics in natural language processing and machine learning have been my primary focus since 2016. I analyze the underpinning mechanisms of information transfer between human society and AI. To investigate the reasoning behind AI representations and outputs, I develop evaluation methods and transparency enhancing approaches that detect, quantify, and characterize human-like associations and biases learned by machines. I study human-AI bias interaction to uncover how machines that automatically learn implicit associations impact humans and society. As AI is co-evolving with society, my goal is to ensure that AI is developed and deployed responsibly, with consideration given to societal implications.

News

  • In 2023, I was recognized as one of the 100 Brilliant Women in AI Ethics and honored with an IJCAI Early Career Spotlight.
  • In Winter 2024, I will give keynotes at UCSF School of Medicine and AIBSD AAAI, and a Seminal Presentation on Bias in AI and ML at Howard University. In Autumn 2023, I will deliver a keynote on AI Ethics at the Artificial Intelligence in Health Professions Education Symposium, organized by the University of Washington's School of Medicine.
  • I am teaching INFO 371 and INSC 578 in Autumn 2023: Advanced Methods in Data Science - Machine Learning and the AI Bias Feedback Cycle.
  • My paper on implicit bias in AI is published in Science. Semantics derived automatically from language corpora contain human-like biases.
    source code
    Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan.

    A Story of Discrimination and Unfairness: Implicit Bias Embedded in Language Models.

    9th Hot Topics in Privacy Enhancing Technologies

    Accepted on 5/20/2016

  • I am the moderator of Computer Science - Computers and Society on arXiv.
  • Research

  • Aylin Caliskan and Kristian Lum
    Effective AI regulation requires understanding general-purpose AI
    Brookings 2024
  • Tessa Elizabeth Sadie Charlesworth, Kshitish Ghate, Aylin Caliskan, and Mahzarin R. Banaji
    Extracting Intersectional Stereotypes from Static and Contextualized Embeddings
    forthcoming, PNAS Nexus 2024
  • Inyoung Cheong, Aylin Caliskan, and Tadayoshi Kohno
    Safeguarding Human Values: Rethinking US Law for Generative AI's Societal Impacts
    forthcoming, AI and Ethics 2024
  • Aylin Caliskan
    Artificial Intelligence, Bias, and Ethics
    The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023)
    IJCAI Early Career Spotlight Paper
  • Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan
    Demographic Stereotypes in Text-to-Image Generation
    Stanford University Human-Centered Artificial Intelligence Policy Brief 2023
  • Isaac Slaughter, Craig Greenberg, Reva Schwartz, and Aylin Caliskan
    Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition
    In Findings of the Association for Computational Linguistics: EMNLP 2023
  • Sourojit Ghosh and Aylin Caliskan
    'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion
    In Findings of the Association for Computational Linguistics: EMNLP 2023
  • Sourojit Ghosh and Aylin Caliskan
    ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2023)
  • Shiva Omrani Sabbaghi, Robert Wolfe, and Aylin Caliskan
    Evaluating Biased Attitude Associations of Language Models in an Intersectional Context
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2023)
  • Robert Wolfe, Yiwei Yang, Bill Howe, and Aylin Caliskan
    Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2023)
  • Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, and Aylin Caliskan
    Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2023)
  • Katelyn X. Mei, Sonia Fereidooni, and Aylin Caliskan
    Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2023)
  • Inyoung Cheong, Aylin Caliskan, and Tadayoshi Kohno
    Envisioning Legal Mitigations for Intentional and Unintentional Harms Associated with Large Language Models (Extended Abstract)
    Fortieth International Conference on Machine Learning Workshop on Generative AI and Law (ICML GenLaw 2023)
  • Yiwei Yang, Anthony Zhe Liu, Robert Wolfe, Aylin Caliskan, and Bill Howe
    Regularizing Model Gradients with Concepts to Improve Robustness to Spurious Correlations (Poster)
    Fortieth International Conference on Machine Learning Workshop on Spurious Correlations, Invariance, and Stability (ICML SCIS 2023)
  • Aylin Caliskan and Ryan Steed
    Managing the risks of inevitably biased visual artificial intelligence systems
    Brookings 2022
  • Tessa Charlesworth, Aylin Caliskan, and Mahzarin R. Banaji
    Historical Representations of Social Groups Across 200 Years of Word Embeddings from Google Books
    Proceedings of the National Academy of Sciences (PNAS 2022)
  • Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, and Mahzarin R. Banaji
    Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2022)
  • Robert Wolfe and Aylin Caliskan
    American == White in Multimodal Language-and-Image AI
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2022)
  • Shiva Omrani Sabbaghi and Aylin Caliskan
    Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2022)
  • Robert Wolfe, Mahzarin R. Banaji, and Aylin Caliskan
    Evidence for Hypodescent in Visual Semantic AI
    The 2022 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2022)
  • Robert Wolfe and Aylin Caliskan
    Markedness in Visual Semantic AI
    The 2022 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2022)
  • Robert Wolfe and Aylin Caliskan
    Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
    60th Annual Meeting of the Association for Computational Linguistics (ACL 2022)
  • Robert Wolfe and Aylin Caliskan
    VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
    Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022)
  • Robert Wolfe and Aylin Caliskan
    Detecting Emerging Associations and Behaviors With Regional and Diachronic Word Embeddings
    16th IEEE International Conference on Semantic Computing (ICSC 2022)
  • Ryan Wails, Andrew Stange, Eliana Troper, Aylin Caliskan, Roger Dingledine, Rob Jansen, and Micah Sherr
    Learning to Behave: Improving Covert Channel Security with Behavior-Based Designs
    Privacy Enhancing Technologies Symposium (PETS 2022)
  • Robert Wolfe and Aylin Caliskan
    Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
    Empirical Methods in Natural Language Processing (EMNLP 2021)
  • Autumn Toney-Wails and Aylin Caliskan
    ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries
    Empirical Methods in Natural Language Processing (EMNLP 2021)
  • Aylin Caliskan and Molly Lewis
    Social biases in word embeddings and their relation to human cognition
    Book Chapter in The Handbook of Language Analysis in Psychology. Guilford Press, 2021
    Editors Morteza Dehghani and Ryan Boyd
  • Aylin Caliskan
    Detecting and mitigating bias in natural language processing
    Brookings 2021
  • Akshat Pandey and Aylin Caliskan
    Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2021)
  • Wei Guo and Aylin Caliskan
    Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases
    AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES 2021)
  • Ryan Steed and Aylin Caliskan
    Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
    The 2021 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2021)
  • Ryan Steed and Aylin Caliskan
    A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild
    AI and Ethics, 2021
  • Autumn Toney, Akshat Pandey, Wei Guo, David Broniatowski, and Aylin Caliskan
    Automatically Characterizing Targeted Information Operations Through Biases Present in Discourse on Twitter
    15th IEEE International Conference on Semantic Computing (ICSC 2021)




  • Privacy | Terms