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, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, 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.
no code implementations • 8 Feb 2024 • Christoph Tillmann, Aashka Trivedi, Bishwaranjan Bhattacharjee
This is unacceptable in civil discourse. The detection of Hate, Abuse and Profanity in text is a vital component of creating civil and unbiased LLMs, which is needed not only for English, but for all languages.
no code implementations • 12 Jan 2024 • Md Arafat Sultan, Aashka Trivedi, Parul Awasthy, Avirup Sil
We present a large-scale empirical study of how choices of configuration parameters affect performance in knowledge distillation (KD).
no code implementations • 18 Dec 2023 • Christoph Tillmann, Aashka Trivedi, Sara Rosenthal, Santosh Borse, Rong Zhang, Avirup Sil, Bishwaranjan Bhattacharjee
Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web.
no code implementations • 13 Oct 2023 • Takuma Udagawa, Aashka Trivedi, Michele Merler, Bishwaranjan Bhattacharjee
Our target of study includes Output Distribution (OD) transfer, Hidden State (HS) transfer with various layer mapping strategies, and Multi-Head Attention (MHA) transfer based on MiniLMv2.
no code implementations • 16 Mar 2023 • Aashka Trivedi, Takuma Udagawa, Michele Merler, Rameswar Panda, Yousef El-Kurdi, Bishwaranjan Bhattacharjee
In each episode of the search process, a NAS controller predicts a reward based on the distillation loss and latency of inference.