大语言模型在线策略蒸馏研究综述 A Survey of On-Policy Distillation for Large Language Models.pdfVIP

  • 1
  • 0
  • 约18.29万字
  • 约 39页
  • 2026-05-19 发布于广东
  • 举报

大语言模型在线策略蒸馏研究综述 A Survey of On-Policy Distillation for Large Language Models.pdf

Preprint.

ASurveyofOn-PolicyDistillationforLargeLanguageModels

MingyangSongMaoZheng

LargeLanguageModelDepartment

Tencent,China

nickmysong@

Abstract

Knowledgedistillationhasbecomeaprimarymechanismfortransferring

6reasoninganddomainexpertisefromfrontierLargeLanguageModels

2

您可能关注的文档

文档评论(0)

1亿VIP精品文档

相关文档