Language Models Can Rewrite Their Own Weights
- Authors:Jiajun Fan, Neil He, Changyi Yang, Andy Mao, Xi Zhu, Chaoran Cheng, Kaiqu Liang, Shuaike Shen, Zetian Li, Ruihan Guo, Ge Liu View PDF HTML (experimental) Abstract:A language model is trained once and frozen.
- Making it better takes another training run, or a prompt, a harness or extra computation at inference that is gone once the task ends.
- We show a third way: to our knowledge for the first time, a language model rewrites its own weights by its own reasoning and becomes better, with no gradients and no training.
Unverified
- Authors:Jiajun Fan, Neil He, Changyi Yang, Andy Mao, Xi Zhu, Chaoran Cheng, Kaiqu Liang, Shuaike Shen, Zetian Li, Ruihan Guo, Ge Liu View PDF HTML (experimental) Abstract:A language model is trained once and frozen.
- Making it better takes another training run, or a prompt, a harness or extra computation at inference that is gone once the task ends.
- We show a third way: to our knowledge for the first time, a language model rewrites its own weights by its own reasoning and becomes better, with no gradients and no training.
Sources: Arxiv