← all papers · overview

How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities, but updating their knowledge post-training remains a critical challenge. While recent model editing techniques like Rank-One Model Editing (ROME) show promise, their effectiveness may vary based on the nature of the knowledge being edited. We introduce the concept of ``perplexingness'': the degree to which new knowledge confli

Related papers

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