用模拟框架研究大模型在选举中的说服行为
ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems
- 构建真实社交平台模拟环境，测试大模型的25种说服技巧
- 不同模型间说服效果差异明显，体现架构与训练的影响
- 发现'真相核心'等现象，适合关注AI伦理与社会影响的研究者
本文提出ElecTwit，一个用于研究多智能体系统中说服行为的仿真框架，专门模拟政治选举期间社交媒体上的互动。通过构建真实情境，克服了以往研究依赖游戏化模拟的局限。实验发现，大多数测试的大语言模型全面运用了25种具体说服技巧，涵盖范围超过以往报告。不同模型在技巧使用和整体说服输出上的差异，凸显了模型架构与训练方式对现实社会仿真动态的影响。此外，观察到如'真相核心'消息及集体追求文字证据的'墨水执念'等独特现象。本研究为评估大模型在真实场景下的说服能力提供了基础，有助于确保其对齐性并防范潜在风险。
原文摘要 · Abstract (English)
This paper introduces ElecTwit, a simulation framework designed to study persuasion within multi-agent systems, specifically emulating the interactions on social media platforms during a political election. By grounding our experiments in a realistic environment, we aimed to overcome the limitations of game-based simulations often used in prior research. We observed the comprehensive use of 25 specific persuasion techniques across most tested LLMs, encompassing a wider range than previously reported. The variations in technique usage and overall persuasion output between models highlight how different model architectures and training can impact the dynamics in realistic social simulations. Additionally, we observed unique phenomena such as "kernel of truth" messages and spontaneous developments with an "ink" obsession, where agents collectively demanded written proof. Our study provides a foundation for evaluating persuasive LLM agents in real-world contexts, ensuring alignment and preventing dangerous outcomes.
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。