用大模型自动优化另一大模型的优化器，提升任务表现
metaTextGrad: Automatically optimizing language model optimizers
- 用元提示和元结构双重优化现有语言模型优化器
- 在多个基准上平均提升6%性能，最高达6个百分点
- 适合需要定制化优化器的特定任务场景
大型语言模型（LLMs）越来越多地用于学习算法、评估和优化任务。近期研究表明，使用基于LLM的优化器自动优化模型提示、示范、预测或其他组件，能显著提升AI系统性能，如DSPy和TextGrad框架所示。然而，这些基于语言模型的优化器通常由人工手动设计，自身未被优化，且因通用性设计而无法针对特定任务调优。为此，我们提出metaTextGrad，旨在设计一个元优化器，进一步增强现有优化器并使其适配特定任务。该方法包含两个核心组件：元提示优化器与元结构优化器。两者结合在多个基准测试中显著提升性能，相比最佳基线平均绝对提升高达6%。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstrations, predictions themselves, or other components can significantly enhance the performance of AI systems, as demonstrated by frameworks such as DSPy and TextGrad. However, optimizers built on language models themselves are usually designed by humans with manual design choices; optimizers themselves are not optimized. Moreover, these optimizers are general purpose by design, to be useful to a broad audience, and are not tailored for specific tasks. To address these challenges, we propose metaTextGrad, which focuses on designing a meta-optimizer to further enhance existing optimizers and align them to be good optimizers for a given task. Our approach consists of two key components: a meta prompt optimizer and a meta structure optimizer. The combination of these two significantly improves performance across multiple benchmarks, achieving an average absolute performance improvement of up to 6% compared to the best baseline.
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。