Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper
•
2407.18248
•
Published
•
31
•
4
Tianduo Wang
Tianduo
AI & ML interests
nlp, representation learning
Recent Activity
liked
a dataset
about 1 month ago
neuralwork/arxiver
Organizations
Tianduo's activity
commented
a
paper
4 months ago