no code implementations • 8 Apr 2024 • Aida Mostafazadeh Davani, Sagar Gubbi, Sunipa Dev, Shachi Dave, Vinodkumar Prabhakaran
We argue that understanding the sentential context is crucial for detecting instances of generalization.
no code implementations • 8 Mar 2024 • Mukul Bhutani, Kevin Robinson, Vinodkumar Prabhakaran, Shachi Dave, Sunipa Dev
While generative multilingual models are rapidly being deployed, their safety and fairness evaluations are largely limited to resources collected in English.
no code implementations • 12 Jan 2024 • Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
First, we show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes, and that the offensiveness of these depictions is especially higher for identities from Africa, South America, and South East Asia.
1 code implementation • 19 May 2023 • Akshita Jha, Aida Davani, Chandan K. Reddy, Shachi Dave, Vinodkumar Prabhakaran, Sunipa Dev
Stereotype benchmark datasets are crucial to detect and mitigate social stereotypes about groups of people in NLP models.
1 code implementation • 17 May 2023 • Rohan Anil, Andrew M. Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, Eric Chu, Jonathan H. Clark, Laurent El Shafey, Yanping Huang, Kathy Meier-Hellstern, Gaurav Mishra, Erica Moreira, Mark Omernick, Kevin Robinson, Sebastian Ruder, Yi Tay, Kefan Xiao, Yuanzhong Xu, Yujing Zhang, Gustavo Hernandez Abrego, Junwhan Ahn, Jacob Austin, Paul Barham, Jan Botha, James Bradbury, Siddhartha Brahma, Kevin Brooks, Michele Catasta, Yong Cheng, Colin Cherry, Christopher A. Choquette-Choo, Aakanksha Chowdhery, Clément Crepy, Shachi Dave, Mostafa Dehghani, Sunipa Dev, Jacob Devlin, Mark Díaz, Nan Du, Ethan Dyer, Vlad Feinberg, Fangxiaoyu Feng, Vlad Fienber, Markus Freitag, Xavier Garcia, Sebastian Gehrmann, Lucas Gonzalez, Guy Gur-Ari, Steven Hand, Hadi Hashemi, Le Hou, Joshua Howland, Andrea Hu, Jeffrey Hui, Jeremy Hurwitz, Michael Isard, Abe Ittycheriah, Matthew Jagielski, Wenhao Jia, Kathleen Kenealy, Maxim Krikun, Sneha Kudugunta, Chang Lan, Katherine Lee, Benjamin Lee, Eric Li, Music Li, Wei Li, Yaguang Li, Jian Li, Hyeontaek Lim, Hanzhao Lin, Zhongtao Liu, Frederick Liu, Marcello Maggioni, Aroma Mahendru, Joshua Maynez, Vedant Misra, Maysam Moussalem, Zachary Nado, John Nham, Eric Ni, Andrew Nystrom, Alicia Parrish, Marie Pellat, Martin Polacek, Alex Polozov, Reiner Pope, Siyuan Qiao, Emily Reif, Bryan Richter, Parker Riley, Alex Castro Ros, Aurko Roy, Brennan Saeta, Rajkumar Samuel, Renee Shelby, Ambrose Slone, Daniel Smilkov, David R. So, Daniel Sohn, Simon Tokumine, Dasha Valter, Vijay Vasudevan, Kiran Vodrahalli, Xuezhi Wang, Pidong Wang, ZiRui Wang, Tao Wang, John Wieting, Yuhuai Wu, Kelvin Xu, Yunhan Xu, Linting Xue, Pengcheng Yin, Jiahui Yu, Qiao Zhang, Steven Zheng, Ce Zheng, Weikang Zhou, Denny Zhou, Slav Petrov, Yonghui Wu
Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.
Ranked #1 on Question Answering on StrategyQA
no code implementations • 21 Nov 2022 • Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, Vinodkumar Prabhakaran
Recent research has revealed undesirable biases in NLP data and models.
no code implementations • 13 Oct 2022 • Abhijeet Awasthi, Nitish Gupta, Bidisha Samanta, Shachi Dave, Sunita Sarawagi, Partha Talukdar
Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training task-specific multilingual models.
1 code implementation • 25 Sep 2022 • Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, Vinodkumar Prabhakaran
In this paper, we focus on NLP fair-ness in the context of India.
no code implementations • 14 Sep 2022 • Kartikeya Badola, Shachi Dave, Partha Talukdar
We address this challenge by proposing LAFT-URIEL, a parameter-efficient finetuning strategy which aims to increase the number of languages on which the model improves after an update, while reducing the magnitude of loss in performance for the remaining languages.
1 code implementation • 19 Mar 2021 • Simran Khanuja, Diksha Bansal, Sarvesh Mehtani, Savya Khosla, Atreyee Dey, Balaji Gopalan, Dilip Kumar Margam, Pooja Aggarwal, Rajiv Teja Nagipogu, Shachi Dave, Shruti Gupta, Subhash Chandra Bose Gali, Vish Subramanian, Partha Talukdar
This can be explained by the fact that multilingual language models (LMs) are often trained on 100+ languages together, leading to a small representation of IN languages in their vocabulary and training data.