arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03408cs.AIcs.CLcs.CYcs.MA
收藏

军事与外交决策中语言模型带来的升级风险

Escalation Risks from Language Models in Military and Diplomatic Decision-Making

Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学);Northeastern University(东北大学)

Juan-Pablo Rivera, Gabriel Mukobi, Anka Reuel, Max Lamparth, Chandler Smith, Jacquelyn Schneider

AI总结:

本文通过设计兵棋推演模拟框架,定量与定性分析了五种大语言模型在军事外交决策中的升级行为,发现其存在军备竞赛乃至核部署风险,建议部署前审慎评估。

摘要:

各国政府正日益考虑在高风险的军事与外交政策决策中集成自主AI智能体,尤其是随着GPT-4等先进生成式AI模型的出现。我们的工作旨在审视多个AI智能体在模拟兵棋推演中的行为,特别关注它们采取可能加剧多边冲突的升级行动的倾向。借鉴政治学和国际关系文献中关于升级动态的研究,我们设计了一个新颖的兵棋推演模拟与评分框架,以评估这些智能体在不同场景中所采取行动的升级风险。与先前研究不同,我们的研究同时提供了定性和定量见解,并聚焦于大语言模型(LLMs)。我们发现,所研究的全部五个现成LLM均表现出升级形式和难以预测的升级模式。我们观察到,模型倾向于发展军备竞赛动态,导致更大冲突,在罕见情况下甚至导致核武器的部署。在定性方面,我们还收集了模型对所选行动所报告的理由,并观察到基于威慑和先发制人打击策略的令人担忧的辩护。鉴于军事和外交政策背景的高风险,我们建议在将自主语言模型智能体部署用于战略军事或外交决策之前,进行进一步审查和审慎考虑。

英文摘要:

Governments are increasingly considering integrating autonomous AI agents in high-stakes military and foreign-policy decision-making, especially with the emergence of advanced generative AI models like GPT-4. Our work aims to scrutinize the behavior of multiple AI agents in simulated wargames, specifically focusing on their predilection to take escalatory actions that may exacerbate multilateral conflicts. Drawing on political science and international relations literature about escalation dynamics, we design a novel wargame simulation and scoring framework to assess the escalation risks of actions taken by these agents in different scenarios. Contrary to prior studies, our research provides both qualitative and quantitative insights and focuses on large language models (LLMs). We find that all five studied off-the-shelf LLMs show forms of escalation and difficult-to-predict escalation patterns. We observe that models tend to develop arms-race dynamics, leading to greater conflict, and in rare cases, even to the deployment of nuclear weapons. Qualitatively, we also collect the models' reported reasonings for chosen actions and observe worrying justifications based on deterrence and first-strike tactics. Given the high stakes of military and foreign-policy contexts, we recommend further examination and cautious consideration before deploying autonomous language model agents for strategic military or diplomatic decision-making.

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。

↑