用随机验证法优化大模型专属经验，提升任务表现且无需改参数。
SEO: Stochastic Experience Optimization for Large Language Models
- 通过自然语言迭代更新经验，不修改模型参数
- 在3个任务上均实现性能持续提升，优于传统方法
- 优化后经验可泛化到分布外数据，适合实际部署
大语言模型（LLMs）可通过有效经验提升特定任务表现，但难以确定哪些经验适合具体模型。以往研究尝试用大模型自动寻找有用经验，但难以保证效果。本文提出随机经验优化（SEO），一种无需修改模型参数、仅通过自然语言更新经验的迭代方法。SEO引入随机验证机制，确保经验更新方向正确，避免无效调整。在三个大模型的三项任务上的实验表明，经SEO优化的经验能持续提升性能。进一步分析显示，这些优化经验具有分布外泛化能力，可增强模型在相似任务上的表现。
原文摘要 · Abstract (English)
Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in natural language. In SEO, we propose a stochastic validation method to ensure the update direction of experience, avoiding unavailing updates. Experimental results on three tasks for three LLMs demonstrate that experiences optimized by SEO can achieve consistently improved performance. Further analysis indicates that SEO-optimized experience can generalize to out-of-distribution data, boosting the performance of LLMs on similar tasks.
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。