Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper
•
2407.18248
•
Published
•
34
Tianduo Wang
Tianduo
AI & ML interests
nlp, representation learning
Recent Activity
upvoted
a
paper
1 day ago
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in
LLMs
upvoted
a
paper
2 days ago
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement
Learning
upvoted
a
paper
9 days ago
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning
Attention
Organizations
