← all papers · overview

The Cost Of Compression: Investigating The Impact Of Compression On Parametric Knowledge In Language Models

Abstract

Compressing large language models (LLMs), often consisting of billions of parameters, provides faster inference, smaller memory footprints, and enables local deployment. Two standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with fewer bits. The key tradeoff is between the degr

Related papers

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