作者位次 #3/10ACL 2026Poster· Natural Language Processing
Two-Stage Regularization-Based Structured Pruning for LLM s
Mingkuan Feng · Jinyang Wu · Siyuan Liu · Shuai Zhang · Hongjian Fang · Ruihan Jin · Feihu Che · Pengpeng Shao · Zhengqi Wen · Jianhua Tao
摘要
The deployment of large language models (LLMs) is largely hindered by their large number of parameters. Structural pruning has emerged as a promising solution. Prior structured pruning methods directly remove unimportant parameters based on certain metrics, which often causes knowledge loss and n...