"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models

arXiv:2403.00180v1 Announce Type: new
Abstract: Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed, and other general behaviors of the model can be wrongly altered. In this work, we investigate how model editing methods unexpectedly amplify model biases post-edit. We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and …

abstract arxiv bias consequences cost cs.cl editing flex general information knowledge language language models misinformation strategy type update