4 citations · 5 across the 14 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Debiasing Multimodal Models via Causal Information Minimization
Vaidehi Patil, Adyasha Maharana, Mohit Bansal
Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow…
cs.CL2023★ 4 cited
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
Vaidehi Patil, Peter Hase, Mohit Bansal
Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They c…