MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation 文章

ArXiv CS.CL2026-05-27NEWSen作者: Haoyu Zheng, Yun Zhu, Shu Yuan, Shangming Chen, Qing Wang, Wenqiao Zhang, Jun Xiao, Yueting Zhuang

大语言模型

查看原文 →

MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation · 相关技术

相关技术

ODE LLM language model rsa divide-and-conquer partitioning TURN TAM Stan Prompt Parts-of-Speech (POS) tags NAT MIT MEC large language models HIS Granular Alignment Paradigm For FOL EFI DiT AnE ARG ANN