@article{uncertaintyawarehybridinferencewithon, title = {Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models}, author = {Seungeun Oh and Jinhyuk Kim and Jihong Park and Seung-Woo Ko and Tony Q. S. Quek and Seong-Lyun Kim}, year = {2024}, eprint = {2412.12687}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.12687v3}, }