← all papers · overview

Unlocking Efficient, Scalable, And Continual Knowledge Editing With Basis-level Representation Fine-tuning

Abstract

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing methods designed to update certain knowledge in LLMs without changing unrelated others. To make selective edits, previous effor

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).