通过残差树结构实现高效多样提示优化，避免性能退化。
RiOT: Efficient Prompt Refinement with Residual Optimization Tree
- 基于文本梯度迭代生成多样提示候选，保持语义丰富性。
- 在五个基准上优于现有方法，数学与逻辑推理提升显著。
- 适合需要稳定高效提示工程的NLP研究与应用者。
大型语言模型在各类任务中展现潜力，但其表现仍高度依赖有效提示设计。现有自动提示优化方法存在多样性不足和语义漂移问题：优化某一任务可能损害其他任务性能。为此，我们提出残差优化树（RiOT）框架，通过文本梯度迭代优化提示，在每步生成多个语义多样候选，并以困惑度选择最优提示。同时引入文本残差连接，有选择性保留优化迭代中的有益内容，缓解语义漂移。树状结构高效管理优化流程，保障可扩展性与灵活性。在涵盖常识、数学、逻辑、时间及语义推理的五个基准上的大量实验表明，RiOT优于以往提示优化方法及人工提示设计。
原文摘要 · Abstract (English)
Recent advancements in large language models (LLMs) have highlighted their potential across a variety of tasks, but their performance still heavily relies on the design of effective prompts. Existing methods for automatic prompt optimization face two challenges: lack of diversity, limiting the exploration of valuable and innovative directions and semantic drift, where optimizations for one task can degrade performance in others. To address these issues, we propose Residual Optimization Tree (RiOT), a novel framework for automatic prompt optimization. RiOT iteratively refines prompts through text gradients, generating multiple semantically diverse candidates at each step, and selects the best prompt using perplexity. Additionally, RiOT incorporates the text residual connection to mitigate semantic drift by selectively retaining beneficial content across optimization iterations. A tree structure efficiently manages the optimization process, ensuring scalability and flexibility. Extensive experiments across five benchmarks, covering commonsense, mathematical, logical, temporal, and semantic reasoning, demonstrate that RiOT outperforms both previous prompt optimization methods and manual prompting.
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。