ValueFlow: 多智能体大语言模型中价值扰动的传播度量
ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
AI总结:
提出ValueFlow框架,通过56维价值数据集和LLM-as-a-judge协议,将价值漂移分解为智能体级响应行为与系统级结构效应,揭示价值对齐是系统级属性。
摘要:
多智能体大语言模型系统日益由观察并响应彼此输出的智能体组成。虽然价值对齐通常针对孤立模型进行评估,但价值扰动如何通过智能体交互传播仍知之甚少。我们提出ValueFlow,一个基于扰动的框架,通过源自施瓦茨价值调查的56维价值数据集,并使用LLM-as-a-judge协议对智能体价值取向进行评分,来度量多智能体系统中的价值漂移。ValueFlow将价值漂移分解为智能体级响应行为和系统级结构效应,由两个指标捕获:\b{eta}-敏感性(智能体对受扰同伴价值信号的敏感度)和系统敏感性(节点级扰动对最终系统输出的影响)。实验跨越价值维度、骨干模型、角色和拓扑,表明敏感性在不同价值间差异显著,并受交互结构强烈影响,表明多智能体系统中的价值对齐是系统级属性,而不仅仅是智能体级属性。因此,ValueFlow为审计和缓解部署的多智能体系统中的价值传播提供了原则性基础。
英文摘要:
Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for isolated models, how value perturbations propagate through agent interactions remains poorly understood. We present ValueFlow, a perturbation-based framework that measures value drift in multi-agent systems via a 56-value valuation dataset derived from the Schwartz Value Survey, with agent value orientations scored using an LLM-as-a-judge protocol. ValueFlow decomposes value drift into agent-level response behavior and system-level structural effects, captured by two metrics: \b{eta}-susceptibility, an agent's sensitivity to perturbed peer value signals, and system susceptibility (SS), the effect of node-level perturbations on final system outputs.Experiments span across value dimensions, backbones, personas, and topologies, showing that susceptibility varies sharply across values and is strongly shaped by interaction structure, indicating that value alignment in multi-agent systems is a system-level property, not just an agent-level one. ValueFlow thus provides a principled basis for auditing and mitigating value propagation in deployed multi-agent systems.
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。