← all papers · overview

Do Compressed Llms Forget Knowledge? An Experimental Study With Practical Implications

Abstract

Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs' inherent knowledge and the possible remedies. We start by proposing two conjectures on the nature of the damage: one is certain knowledge being forgotten (or erased) after LLM compression, hence necessitating the compressed

Related papers

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