Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders 文章

ArXiv CS.CL2026-05-27NEWSen作者: Yi Jing, Zao Dai, Jinwu Hu, Zijun Yao, Lei Hou, Juanzi Li, Xiaozhi Wang
大语言模型
查看原文 →
关系图谱

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders · 相关人物

暂无数据