As mobile applications (i.e., apps) increasingly manage a wide variety of user needs, their access to sensitive data intensifies privacy concerns among users. While app markets employ permissions to regulate the private data access, the lack of explanation of permission uses render this mechanism less successful. Existing techniques that extract explanatory sentences from app descriptions to inform users about sensitive behaviors are also limited, as many app behaviors remain unexplained in their descriptions. To tackle these issues, we propose AppBDS, a novel approach that integrates program analysis with Large Language Models (LLM) to process code semantics and UI contexts, complemented by privacy policies and information from similar apps, to generate detailed explanations for apps’ sensitive behaviors. Specifically, AppBDS integrates code semantics with UI contexts to build a UI-Fused Call Graph (UCG) for each app. Additionally, AppBDS summarizes permission-related propositions from privacy policies and utilizes similar apps’ information from a curated knowledge base (PP-KB) to improve LLMs’ domain knowledge in explaining permission uses. In particular, AppBDS curates the PP-KB by using LLMs to extract permissionrelated propositions and infer permission descriptions of apps from a wide range of categories. Our evaluation results on 270 real apps indicate that AppBDS significantly outperforms state-of-the-art approaches in terms of factuality and semantic richness, as validated through extensive experiments and manual inspection.