Plum: Prompt Learning using Metaheuristic

arXiv:2311.08364v2 Announce Type: replace
Abstract: Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models. Special prompts, such as Chain-of-Thought, have even revealed previously unknown reasoning capabilities within these models. However, the progress of discovering effective prompts has been slow, driving a desire for general prompt optimization methods. Unfortunately, few existing prompt learning methods satisfy the criteria of being truly "general", i.e., automatic, discrete, black-box, gradient-free, and interpretable all at …

arxiv cs.ai cs.dm cs.lg prompt prompt learning type