从机制可解释性出发，为大模型多智能体系统设计伦理保障方案
Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
- 通过机制可解释性分析多智能体行为的内部生成逻辑
- 提出三层次评估框架，覆盖个体、交互与系统级伦理表现
- 探索高效对齐技术，在不损失性能前提下引导伦理行为
大语言模型广泛应用于各类场景，常以自主智能体形式在多智能体系统中协作。这类系统虽能提升能力并完成复杂任务，却也带来显著伦理风险。本文从机制可解释性视角，提出确保大模型多智能体系统（MALMs）伦理行为的研究议程，聚焦三大挑战：(i) 构建覆盖个体、交互与系统层面的综合评估框架；(ii) 运用机制可解释性揭示涌现行为的内在生成机制；(iii) 实施针对性的参数高效对齐方法，在不损害性能的前提下引导系统向伦理方向演化。
原文摘要 · Abstract (English)
Large language models (LLMs) have been widely deployed in various applications, often functioning as autonomous agents that interact with each other in multi-agent systems. While these systems have shown promise in enhancing capabilities and enabling complex tasks, they also pose significant ethical challenges. This position paper outlines a research agenda aimed at ensuring the ethical behavior of multi-agent systems of LLMs (MALMs) from the perspective of mechanistic interpretability. We identify three key research challenges: (i) developing comprehensive evaluation frameworks to assess ethical behavior at individual, interactional, and systemic levels; (ii) elucidating the internal mechanisms that give rise to emergent behaviors through mechanistic interpretability; and (iii) implementing targeted parameter-efficient alignment techniques to steer MALMs towards ethical behaviors without compromising their performance.
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。