作者位次 #6/9ACL 2026Poster· Natural Language Processing
Gradient-Guided Multi-Judge Prompt Optimization
ChenZhuo Zhao · Xinda Wang · Pu Zhao · Yue Huang · Junting Lu · Ziqian Liu · Qingwei Lin · Saravan Rajmohan · Dongmei Zhang
摘要
Automatic prompt optimization is a practical alternative to fine-tuning for adapting large language models (LLMs), yet existing approaches often trade off signal quality against computational cost. Methods that rely on generative feedback can be informative but expensive to scale, while sampling-...