STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification
STEVE, a stabilization framework with two coupled mechanisms that reduces degradation and produces more robust prompts, provides a practical way to improve the stability and effectiveness of textual-gradient prompt optimization.
Yi-Fan Xu, Yi-Xuan Li, Xin-Zhuo Li et al.
· 0 citations