arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08702cs.CLcs.AIcs.HCcs.RO
收藏

多步任务中的提示优化(PROMST):融合人类反馈与基于启发式的采样

PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling

MIT(麻省理工学院);Harvard University(哈佛大学);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)

Yongchao Chen, Jacob Arkin, Yilun Hao, Yang Zhang, Nicholas Roy, Chuchu Fan

AI总结:

本文提出PROMST框架,通过融合人工设计的反馈规则和基于启发式模型的候选提示采样,自动优化多步任务中的LLM提示,在11个任务上显著超越现有方法。

摘要:

提示优化旨在为给定任务找到针对大型语言模型(LLM)的最佳提示。LLM已被成功用于帮助发现和改进单步任务的候选提示。然而,面向智能体的现实任务通常是多步的,并带来了新的挑战:(1)提示内容可能更加冗长和复杂,使LLM更难分析错误;(2)单个步骤的影响难以评估;(3)不同的人可能对任务执行有不同的偏好。虽然人类在优化提示方面存在困难,但他们擅长对LLM输出提供反馈;因此,我们引入了一个新的由LLM驱动的离散提示优化框架——多步任务中的提示优化(PROMST),该框架融合了人工设计的反馈规则,以自动提供直接的改进建议。我们还使用了一个额外的学习式启发式模型来预测提示性能,从而高效地从候选提示中进行采样。该方法在11个具有代表性的多步任务上显著优于人工设计的提示和其他几种提示优化方法(在五个LLM上分别比当前最佳方法平均提升10.6%-29.3%)。我们相信我们的工作可以作为面向LLM驱动的多步任务的自动提示优化基准。数据集和代码可在 https://github.com/yongchao98/PROMST 获取。项目页面可在 https://yongchao98.github.io/MIT-REALM-PROMST 获取。

英文摘要:

Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for single-step tasks. However, realistic tasks for agents are multi-step and introduce new challenges: (1) Prompt content is likely to be more extensive and complex, making it more difficult for LLMs to analyze errors, (2) the impact of an individual step is difficult to evaluate, and (3) different people may have varied preferences about task execution. While humans struggle to optimize prompts, they are good at providing feedback about LLM outputs; we therefore introduce a new LLM-driven discrete prompt optimization framework PRompt Optimization in Multi-Step Tasks (PROMST) that incorporates human-designed feedback rules to automatically offer direct suggestions for improvement. We also use an extra learned heuristic model that predicts prompt performance to efficiently sample from prompt candidates. This approach significantly outperforms both human-engineered prompts and several other prompt optimization methods across 11 representative multi-step tasks (an average 10.6\%-29.3\% improvement to current best methods on five LLMs respectively). We believe our work can serve as a benchmark for automatic prompt optimization for LLM-driven multi-step tasks. Datasets and Codes are available at https://github.com/yongchao98/PROMST. Project Page is available at https://yongchao98.github.io/MIT-REALM-PROMST.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑