Kshitish Ghate

CSE PhD student at the Paul G. Allen School of Computer Science & Engineering - University of Washington.

kshitish.jpg

Hello there!

I am Kshitish Ghate. My research interests lie in developing AI systems that go beyond a “one-size-fits-all” approach to benefit society, with a focus on aligning AI systems with pluralistic human values and preferences.

I am currently a first year PhD student at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where I am fortunate to be advised by Dr. Aylin Caliskan and Dr. Tadayoshi Kohno. Previously, I graduated with a Master’s in Language Technologies from the Language Technologies Institute at Carnegie Mellon University where I was advised by Dr. Mona Diab. I am also grateful to be have been advised thus far by Dr. Maarten Sap, Dr. Fei Fang, Dr. Tessa Charlesworth, Dr. Mahzarin Banaji, and Dr. Snehanshu Saha during my undergradutate and graduate years.

news

Apr 30, 2025 Presenting our paper at NAACL in Albuquerque, New Mexico!
May 13, 2024 I will be returning to UW to pursue my summer research internship where I will be co-advised by Aylin Caliskan and Mona Diab!
Aug 12, 2023 I am starting my Graduate degree in Language Technologies where I will be advised by Mona Diab!
Oct 20, 2022 I will be pursuing my undergraduate thesis under Prof. Aylin Caliskan at the University of Washington!
Mar 15, 2022 I will be starting a part-time position as a research assitant at the Banaji Lab!

selected publications

  1. ACL
    Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes
    Kshitish Ghate, Tessa Charlesworth, Mona T. Diab, and 1 more author
    In Findings of the Association for Computational Linguistics: ACL 2025 Jul 2025
  2. ACL
    REALM: A Dataset of Real-World LLM Use Cases
    Jingwen Cheng, Kshitish Ghate, Wenyue Hua, and 3 more authors
    In Findings of the Association for Computational Linguistics: ACL 2025 Jul 2025
  3. NAACL
    Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders
    Kshitish Ghate, Isaac Slaughter, Kyra Wilson, and 2 more authors
    In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Apr 2025
  4. PNAS Nexus
    Extracting intersectional stereotypes from embeddings: Developing and validating the Flexible Intersectional Stereotype Extraction procedure
    Tessa ES Charlesworth, Kshitish Ghate, Aylin Caliskan, and 1 more author
    PNAS nexus Apr 2024