-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 11 -
gaotang/figlet_font
Viewer • Updated • 45k • 33 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 17 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 22
Gaotang Li
gaotang
AI & ML interests
None yet
Organizations
None yet
Knowledge Conflict
Parametric dataset related to the paper "Taming Knowledge Conflict in Language Models".
Beyond-Log-Likelihood
-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 11 -
gaotang/figlet_font
Viewer • Updated • 45k • 33 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 17 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 22
RM-R1
RM-R1: Reward Modeling as Reasoning
Knowledge Conflict
Parametric dataset related to the paper "Taming Knowledge Conflict in Language Models".