Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
任务分层的知识扩展规律用于训练后量化的大语言模型
机构 * School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院) ; The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所认知与决策智能复杂系统重点实验室) ; School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) ; College of Computer Science, Inner Mongolia University(内蒙古大学计算机学院)
专题命中 预训练与数据 :large language model(title,abstract);language model(title,abstract);post-training(title,abstract);分类 cs.CL、cs.AI、cs.LG
AI总结 本文提出任务分层的知识扩展规律,通过统一模型大小、位宽和细粒度因素,验证了293种不同的训练后量化配置,揭示了不同知识能力对精度、规模和校准的敏感性。
Comments Accepted to Findings of ACL 2026