vix.ing · top · new · best · stats · spec

Shichen Li

  1. Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
    2024/07/25 by Tianduo Wang, Wang, Tianduo, Shichen Li +3 · 4 citations
    Computer Science · #Cognitive Science and Mapping #Computation and Language (cs.CL) #FOS: Computer and information sciences