Plum: Prompt Learning using Metaheuristic

TL;DR

This paper explores using metaheuristic algorithms for prompt learning in large language models, enabling automatic, discrete, black-box, and interpretable prompt optimization, and discovering human-understandable prompts.

Contribution

Introduces metaheuristics as a novel, general approach for prompt learning, demonstrating effectiveness across reasoning and image tasks.

Findings

Metaheuristics effectively optimize prompts in white-box and black-box settings.

Discovered human-understandable prompts previously unknown.

Enhanced prompt optimization broadens possibilities in AI applications.

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 once. In this paper, we introduce metaheuristics, a branch of discrete non-convex optimization methods with over 100 options, as a promising approach to prompt learning. Within our paradigm, we test six typical methods: hill climbing, simulated annealing, genetic algorithms with/without crossover, tabu search, and harmony search, demonstrating their effectiveness in white-box and black-box prompt learning. Furthermore, we show that these methods can be used to discover more human-understandable prompts that were previously unknown in both reasoning and image generation tasks, opening the door to a cornucopia of possibilities in prompt optimization. We release all the codes in \url{https://github.com/research4pan/Plum}.