As the cornerstone for the safe operation of energy systems

short-term voltage stability (STVS) has been assessed effectively with the advance of artificial intelligence (AI). However

the black-box models of traditional AI barely identify what the specific key factors in power systems are and how they influence STVS

thus providing limited practical information for engineers in on-site dispatch centers. Enlightened by the latest explainable artificial intelligence (XAI) techniques

this paper aims to unveil the mechanism underlying the complex STVS problem. First

the ground truth for STVS is established via qualitative analysis. Based on this

an explainability score is then devised to measure the trustworthiness of different XAI techniques

among which Local Interpretable Model-agnostic Explanations (LIME) exhibits the best performance in this study. Finally

a sequential approach is proposed to extend the local interpretation of LIME to a broader scope

which is applied to enhance STVS performance before a fault occurs in distribution system load shedding

serving as an example to demonstrate the application merits of the explored mechanism. Numerical results on a modified IEEE system demonstrate that this finding facilitates the identification of the most suitable XAI technique for STVS

while also providing an interpretable mechanism for the STVS

offering accessible guidance for stability-aware dispatch.