Updates

August 2024 - Our new paper Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models is now available on arXiv

October 2023 - Our paper “Demystifying Prompts in Language Models via Perplexity Estimation” is accepted at Findings of EMNLP (with a few more papers as well)

August 2023 - Women’s Postdoctoral Career Development Award in Science (Weitzmann Institute of Science)

January 2023 - Best Doctoral Dissertation Award Runner Up, Israeli Association for Artificial Intelligence (IAAI)

December 2022 - Our new paper “Demystifying Prompts in Language Models via Perplexity Estimation” is now available on arXiv

October 2022 - Excited to receive the EECS Rising Stars award, attended the workshop at UT Austin

May 2022 - We are honored to get the Best Paper award at the RepL4NLP workshop for our paper “Analyzing Gender Representation in Multilingual Models”

March 2022 - Guest lecture at the NLP course at UW (Prof. Noah A. Smith)

Our “lipstick on a pig” paper is discussed in the book “The Alignment Problem” by Brian Christian

December 2021 - Invited talk at Emily Bender’s group - Subspaces in Multilingual Models

October 2021 - Started postdoctoral research at Meta AI and at UW