分析AI如何决定是否军事干预，发现胜率是核心因素。
The Prompt War: How AI Decides on a Military Intervention
- 用128个情景测试主流大模型的军事决策
- 胜率和国内支持是影响决策的关键因素
- 对平民伤亡敏感，但对经济冲击不敏感
AI在高风险决策中的应用快速增长，但我们仍缺乏对其内在决策驱动因素的系统分析。本文通过共轭实验，让来自OpenAI、Anthropic、Google的大型语言模型（LLMs）在128个情景中判断是否进行军事干预，每个情景重复10次，共生成1280次决策。结果表明，所有模型均高度依赖成功概率和国内支持，远超平民伤亡、经济冲击或国际制裁的影响。进一步测试显示，尽管决策受动机上下文影响，但胜利概率始终是首要考量。此外，模型对平民伤亡规模表现出一定敏感性，但对经济冲击规模无明显反应。
原文摘要 · Abstract (English)
Which factors determine AI's propensity to support military intervention? While the use of AI in high-stakes decision-making is growing exponentially, we still lack systematic analysis of the key drivers embedded in these models. This paper conducts a conjoint experiment in which large language models (LLMs) from leading providers (OpenAI, Anthropic, Google) are asked to decide on military intervention across 128 vignettes, with each vignette run 10 times. This design enables a systematic assessment of AI decision-making in military contexts. The results are remarkably consistent across models: all models place substantial weight on the probability of success and domestic support, prioritizing these factors over civilian casualties, economic shock, or international sanctions. The paper then tests whether LLMs are sensitive to context by introducing different motivations for intervention. The scoring is indeed context-dependent; however, probability of victory remains the most important factor in all scenarios. Finally, the paper evaluates numerical sensitivity and finds that models display some responsiveness to the scale of civilian casualties but no detectable sensitivity to the size of the economic shock.
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。