MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
This addresses the challenge of selecting optimal LLMs for specific tasks, offering a method to leverage multiple models, though it is incremental as it builds on existing genetic algorithm and LLM integration techniques.
The paper tackles the problem of varying LLM performance on complex tasks by introducing MultiGA, a genetic algorithm that uses multi-source seeding from diverse LLMs to refine solutions, achieving convergence to the accuracy of the best-fit LLM for tasks like text-to-SQL and GPQA benchmarks.
Large Language Models (LLMs) are widely used across research domains to tackle complex tasks, but their performance can vary significantly depending on the task at hand. Evolutionary algorithms, inspired by natural selection, can be used to refine solutions iteratively at inference-time. To the best of our knowledge, there has not been exploration on leveraging the collective capabilities of multi-source seeding for LLM-guided genetic algorithms. In this paper, we introduce a novel approach, MultiGA, 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. MultiGA generates a range of outputs from various parent LLMs, open source and closed source, 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. We benchmark our approach using text-to-SQL code generation tasks, trip planning, GPQA benchmark for grad-level science questions, and the BBQ bias benchmark. Our results show that MultiGA converges to the accuracy of the LLM best fit for the task, 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.