no code implementations • 8 Feb 2023 • Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar, Judy Hoffman
We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix.
1 code implementation • 29 Oct 2021 • Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar, Judy Hoffman
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations.