1 code implementation • 9 Jun 2024 • Abdelrahman Zayed, Goncalo Mordido, Ioana Baldini, Sarath Chandar
CAIRO augments the original prompts of a given fairness metric by using several pre-trained language models and then selects the combination of the augmented prompts that achieves the highest correlation across metrics.
no code implementations • 9 Mar 2024 • Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Kirushikesh DB, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Nishtha Madaan, Sameep Mehta, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
1 code implementation • 24 Dec 2023 • Abdelrahman Zayed, Goncalo Mordido, Samira Shabanian, Ioana Baldini, Sarath Chandar
The increasing size of large language models (LLMs) has introduced challenges in their training and inference.
no code implementations • 12 Dec 2023 • Manish Nagireddy, Lamogha Chiazor, Moninder Singh, Ioana Baldini
Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender.
no code implementations • 15 Nov 2023 • Brooklyn Sheppard, Anna Richter, Allison Cohen, Elizabeth Allyn Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong
Using novel approaches to dataset development, the Biasly dataset captures the nuance and subtlety of misogyny in ways that are unique within the literature.
no code implementations • 22 May 2023 • Ioana Baldini, Chhavi Yadav, Manish Nagireddy, Payel Das, Kush R. Varshney
We demonstrate that the newly created dataset BBNLI-next is more challenging than BBNLI: on average, BBNLI-next reduces the accuracy of state-of-the-art NLI models from 95. 3%, as observed by BBNLI, to a strikingly low 57. 5%.
no code implementations • 8 May 2022 • Hammaad Adam, Ming Ying Yang, Kenrick Cato, Ioana Baldini, Charles Senteio, Leo Anthony Celi, Jiaming Zeng, Moninder Singh, Marzyeh Ghassemi
In this study, we investigate the level of implicit race information available to ML models and human experts and the implications of model-detectable differences in clinical notes.
no code implementations • 9 Mar 2022 • Karan Bhanot, Ioana Baldini, Dennis Wei, Jiaming Zeng, Kristin P. Bennett
In this paper, we evaluate the fairness of models generated on two healthcare datasets for gender and race biases.
no code implementations • 7 Dec 2021 • Kofi Arhin, Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Moninder Singh
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise.
no code implementations • Findings (ACL) 2022 • Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Mikhail Yurochkin, Moninder Singh
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
2 code implementations • Findings (ACL) 2021 • Diego Garcia-Olano, Yasumasa Onoe, Ioana Baldini, Joydeep Ghosh, Byron C. Wallace, Kush R. Varshney
Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable.
no code implementations • 18 Nov 2019 • Shivashankar Subramanian, Ioana Baldini, Sushma Ravichandran, Dmitriy A. Katz-Rogozhnikov, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Kush R. Varshney, Annmarie Wang, Pradeep Mangalath, Laura B. Kleiman
More than 200 generic drugs approved by the U. S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer.
no code implementations • 8 Sep 2019 • Yaoli Mao, Dakuo Wang, Michael Muller, Kush R. Varshney, Ioana Baldini, Casey Dugan, AleksandraMojsilović
Our findings suggest that besides the glitches in the collaboration readiness, technology readiness, and coupling of work dimensions, the tensions that exist in the common ground building process influence the collaboration outcomes, and then persist in the actual collaboration process.
no code implementations • 16 Jul 2018 • Evan Patterson, Ioana Baldini, Aleksandra Mojsilovic, Kush R. Varshney
Your computer is continuously executing programs, but does it really understand them?