Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
Comprehensive in-domain and out-of-domain evaluations across multiple LLMs demonstrate that SFS-DPO and SFS-DPO-R consistently outperform prior step-level training baselines and reveal improvements in self-correction frequency and effectiveness.
Duc Anh Vu, Nhat M. Hoang, Do-Xuan Long et al.
· 1 citation