conftrace_

weight attribution

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

model utility (1) gradient difference (1) large language model (1) influence attribution (1) model utility preservation (1) machine unlearning (1) preference optimization (1) knowledge editing (1) gradient-based optimization (1)

Papers

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models NeurIPS 2024