Managing Escalation in Off-the-Shelf Large Language Models (2508.01056v1)

Abstract: U.S. national security customers have begun to utilize LLMs, including enterprise versions of ``off-the-shelf'' models (e.g., ChatGPT) familiar to the public. This uptake will likely accelerate. However, recent studies suggest that off-the-shelf LLMs frequently suggest escalatory actions when prompted with geopolitical or strategic scenarios. We demonstrate two simple, non-technical interventions to control these tendencies. Introducing these interventions into the experimental wargame design of a recent study, we substantially reduce escalation throughout the game. Calls to restrict the use of LLMs in national security applications are thus premature. The U.S. government is already, and will continue, employing LLMs for scenario planning and suggesting courses of action. Rather than warning against such applications, this study acknowledges the imminent adoption of LLMs, and provides actionable measures to align them with national security goals, including escalation management.