Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
Paper
• 2407.18248 • Published
• 33
shichen
scli-21
AI & ML interests
nlp,llm
Recent Activity
authored
a paper
1 day ago
Self-Training with Direct Preference Optimization Improves
Chain-of-Thought Reasoning authored
a paper
1 day ago
AutoFigure-Edit: Generating Editable Scientific Illustration upvoted a paper 1 day ago
AutoFigure-Edit: Generating Editable Scientific Illustration Organizations
authored 2 papers 1 day ago