How Post-Training Shapes Biological Reasoning Models
Post-training stages in biological reasoning models differently affect generalization, with continued pre-training aligning models with biological language, supervised fine-tuning…
Hugging Face · Daily Papers
·Lukas Fesser, Hanlin Zhang
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Lukas Fesser, Hanlin Zhang, Michelle M. Li, Eric Wang, Bryan Perozzi, Shekoofeh Azizi
- 3 upvotes da comunidade
- Temas: language models, foundation models, multimodal biological data, post-training, continued pre-training, supervised fine-tuning
Resumo
Resumo original (em inglês), extraído do paper:
Post-training stages in biological reasoning models differently affect generalization, with continued pre-training aligning models with biological language, supervised fine-tuning improving in-domain performance but reducing out-of-domain generalization, and reinforcement learning recovering out-of-domain performance when applied to well-aligned checkpoints.Onde ler
// relacionados
