MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms

TL;DR

MultiGA is a novel optimization framework that enhances natural language tasks by combining diverse LLM outputs through genetic algorithm principles, leading to improved accuracy.

Contribution

It introduces a method to leverage multiple LLMs for initialization and iterative refinement in genetic algorithms, which is a new approach in this context.

Findings

MultiGA achieves high accuracy across multiple benchmarks.

Diverse LLM sampling improves solution quality.

Framework lays groundwork for multi-LLM integration in complex tasks.

Abstract

In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal.