Zhan, J. et al. 2026. PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 33 (Mar. 2026), 28150–28158. DOI:https://doi.org/10.1609/aaai.v40i33.40041.