用多个大模型生成初始解，提升复杂语言任务求解精度
MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
- 从多个大模型采样初始化遗传算法种群
- 在多基准测试中实现高准确率，优于单一模型
- 适合需要多模型协同的复杂推理任务
本文提出MultiGA，一种优化框架，通过从多个大语言模型（LLMs）中采样生成初始候选解，应用遗传算法原理解决复杂的自然语言任务与推理问题。该方法利用多样化的父代模型生成多种输出，并采用中性适应度函数进行评估。通过迭代重组过程，不断混合与优化生成结果，直至获得最优解。实验表明，MultiGA在多个基准测试中均展现出高准确率，为未来探索多模型集成在未充分研究任务中的应用奠定了基础，尤其适用于仅依赖单一预训练模型时效果不明确或次优的情况。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。