3 papers
cs.CL2025
Resolving Lexical Bias in Model Editing
Hammad Rizwan, Domenic Rosati, Ga Wu +1
Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can res…
cs.LG2025
Data-centric Prediction Explanation via Kernelized Stein Discrepancy
Mahtab Sarvmaili, Hassan Sajjad, Ga Wu
Existing example-based prediction explanation methods often bridge test and training data points through the model's parameters or latent representations. While these methods offer…
cs.LG2025
Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad +1
Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of…