DPO STAR for math Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning Paper • 2407.18248 • Published Jul 25, 2024 • 33
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning Paper • 2407.18248 • Published Jul 25, 2024 • 33
DPO STAR for math Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning Paper • 2407.18248 • Published Jul 25, 2024 • 33
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning Paper • 2407.18248 • Published Jul 25, 2024 • 33
