Zeng, Ziqian, et al. “ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 17, Mar. 2024, pp. 19506-14, doi:10.1609/aaai.v38i17.29922.