News

Mar 2026 Check out our new preprint Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models, which talks about memorization, misalignment, and copyright law. [paper] [code] [website]
Apr 2025 I will start my PhD journey at Stony Brook University in Fall 2025. I am excited to be advised by Tuhin Chakrabarty.
Jul 2024 Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning has been accepted to the 17th International Natural Language Generation Conference (INLG). [paper] [data & code] [demo]