Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper
•
2510.00526
•
Published
•
8
Gaotang Li
gaotang
AI & ML interests
None yet
Recent Activity
authored
a paper
26 days ago
Beyond Log Likelihood: Probability-Based Objectives for Supervised
Fine-Tuning across the Model Capability Continuum
liked
a dataset
26 days ago
zwhe99/DeepMath-103K
upvoted
a
paper
26 days ago
TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular
Reasoning
Organizations
None yet
authored
a
paper
26 days ago
authored
a
paper
5 months ago
authored
a
paper
6 months ago