From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection
英文标题：From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection
arXiv:2608.25243v1 Announce Type: new Abstract: Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fine-tuning (SFT), which memorizes injected facts in their training format but fails to generalize ac
打开原文相关 1.6 · 机会 0
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2608.25243v1 Announce Type: new Abstract: Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fine-tuning (SFT), which memorizes injected facts in their training format but fails to generalize ac
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×