Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper
•
2510.00526
•
Published
•
8
Kamran Vojislav
angrydog111
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 months ago
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety
Assurance
Organizations
None yet
upvoted
a
paper
11 days ago