About

I am a Senior Research Scientist at Google Research working at the Technology, AI, Society, and Culture (TASC) team at the Responsible AI and Human Centered Technologies organization. My research is at the intersection of language, AI, and society. I work towards the goal of safe, inclusive, robust, and trustworthy AI. Some of my current objectives are grouding evaluations of generative models in real world experiences, and contextualizing them with diverse global perspectives and socio-cultural differences. I investigate and develop complementary socio-tecnhonal approaches to imbue an understanding of fairness across different fluid, and intersectional identities of people into robust, scalable measurements, and harm mitigations.

Prior to this, I was an NSF Computing Innovation Fellow at Dr. Kai-Wei Chang 's lab at UCLA, before which I completed my PhD under the guidance of Dr. Jeff Phillips at the School of Computing in University of Utah.

A full list of my publications can be found here. The best way to reach me is at sunipadev [AT] google [DOT] com.

News

• I will be in Singapore for EMNLP 2023 where I will be organizing WiNLP . Come say hi!
• I have been promoted to Senior Research Scientist at Google Research in October 2023.
• We will be organizing the 2nd Workshop on Cross Cultural Considerations in NLP at ACL 2024 in August at Bangkok, and the 3rd Workshop on HCI + NLP at NAACL 2024 in May at Mexico City. More detials about both to follow!
• Our paper on community engaged stereotype evaluation resources has been accepted at NeurIPS 2023 .
• We had three papers accepted at ACL 2023. One investigated robustness of bias measurements in NLP (won Outstanding Paper Award), second built a scalable stereotype evaluation resource by leveraging LLMs, and the third investigated the extent of misgendering in language models.