๐จ Paper Alert
๐น๐น๐น๐น๐น๐น๐น๐น๐น
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
๐น๐น๐น๐น๐น๐น๐น๐น๐น
๐ https://arxiv.org/pdf/2501.17703
@css_nlp
Post #109
5.3K
- ๐ 3
- โค 1
- ๐ 1