no code implementations • 17 Jan 2024 • Niklas Mannhardt, Elizabeth Bondi-Kelly, Barbara Lam, Chloe O'Connell, Mercy Asiedu, Hussein Mozannar, Monica Agrawal, Alejandro Buendia, Tatiana Urman, Irbaz B. Riaz, Catherine E. Ricciardi, Marzyeh Ghassemi, David Sontag
Augmentations were evaluated for errors by clinicians, and we found misleading errors occur, with errors more common in real donated notes than synthetic notes, illustrating the importance of carefully written clinical notes.
1 code implementation • 19 Oct 2022 • Stefan Hegselmann, Alejandro Buendia, Hunter Lang, Monica Agrawal, Xiaoyi Jiang, David Sontag
We study the application of large language models to zero-shot and few-shot classification of tabular data.
no code implementations • WS 2020 • Liqun Shao, Sahitya Mantravadi, Tom Manzini, Alejandro Buendia, Manon Knoertzer, Soundar Srinivasan, Chris Quirk
In this paper, we detail novel strategies for interpolating personalized language models and methods to handle out-of-vocabulary (OOV) tokens to improve personalized language models.