arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.03359cs.AI
收藏

增强大语言模型指令遵循：一种以评估为导向的多智能体工作流用于提示指令优化

Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization

Card Intelligence, Capital One（卡德智能，Capital One）

Alberto Purpura, Li Wang, Sahil Badyal, Eugenio Beaufrand, Adam Faulkner

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了一种多智能体工作流，通过评估驱动的方法优化提示指令，提升大语言模型对约束条件的遵循能力。

摘要：

大型语言模型（LLMs）常常生成实质性相关的内容，但难以遵守正式约束，导致输出在概念上正确但过程上存在缺陷。传统提示优化方法专注于重新表述LLM需要执行的主要任务的描述，忽视了作为响应接受标准的细粒度约束。我们提出了一种新的多智能体工作流，将主要任务描述的优化与其约束分开，利用定量分数作为反馈，迭代地重写和改进它们。我们的评估表明，该方法产生的修订提示在LLaMA 3.1 8B和Mixtral-8x 7B等模型上产生了显著更高的符合分数。

英文摘要：

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on rephrasing the description of the primary task an LLM has to perform, neglecting the granular constraints that function as acceptance criteria for its response. We propose a novel multi-agentic workflow that decouples optimization of the primary task description from its constraints, using quantitative scores as feedback to iteratively rewrite and improve them. Our evaluation demonstrates this method produces revised prompts that yield significantly higher compliance scores from models like Llama 3.1 8B and Mixtral-8x 7B.

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。

↑