作者位次 #3/5ACL 2026Poster· Natural Language Processing
LBLLM : Lightweight Binarization of Large Language Models via Three-Stage Distillation
Siqing Song · Chuang Wang · Yong Lang · YI YANG · Xu-yao Zhang
摘要
Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization through a novel three-stage quantization strategy. The frame...