Signed in
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
| $20.11% | |
| $0.940.06% | |
| $0.480.03% | |
| $0.170.01% | |
| $0.120.01% | |
| $0.010.00% | |
| $0.000.00% | |
| $0.000.00% | |
| $0.000.00% | |
| $0.000.00% |
SEAL (Self-Adapting LLMs) is a framework for training language models via RL to generate self-edits (finetuning data and other update directives for themselves) in response to new inputs.