Do Compressed LLMs Forget Knowledge? An Experimental Study with
Practical Implications

v1v2v3 (latest)

Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications

2 October 2023

Minsik Cho

Mohammad Rastegari

ArXiv (abs)PDF HTML

Papers citing "Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications"

4 / 4 papers shown

Title
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training Ziqiao Wang Wangbo Zhao Yuhao Zhou Zekai Li Zhiyuan Liang ... Pengfei Zhou Kai Zhang Zhangyang Wang Kai Wang Yang You 92 0 0 22 May 2025
Introspective Growth: Automatically Advancing LLM Expertise in Technology Judgment Siyang Wu Honglin Bao Nadav Kunievsky James A. Evans 132 0 0 18 May 2025
Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces Michael Pichat William Pogrund Paloma Pichat Judicael Poumay Armanouche Gasparian Samuel Demarchi Martin Corbet Alois Georgeon Michael Veillet-Guillem MILM 89 0 0 30 Apr 2025
Composable Interventions for Language Models Arinbjorn Kolbeinsson Kyle O'Brien Tianjin Huang Shanghua Gao Shiwei Liu ... Anurag J. Vaidya Faisal Mahmood Marinka Zitnik Tianlong Chen Thomas Hartvigsen KELM MU 197 4 0 09 Jul 2024