@inproceedings{lim-etal-2026-hyperion,
    title = "Hyperion: Private Token Sampling with Homomorphic Encryption",
    author = "Lim, Lawrence  and
      Liu, Jiaming  and
      Kalagi, Vikas  and
      Agrawal, Divyakant  and
      El Abbadi, Amr",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.644/",
    pages = "14150--14159",
    ISBN = "979-8-89176-390-6",
    abstract = "A promising direction for enabling private queries to large language models (LLMs) is with homomorphic encryption (HE). An open problem is performing token sampling under HE. In this paper, we introduce Hyperion, an efficient HE algorithm for inverse transform sampling, enabling private token sampling with 1 comparison depth, $O(1)$ amortized comparisons, and $O(\log n)$ rotations. We implement our approach and demonstrate that it samples tokens in 0.14 seconds for 32k tokens ($\approx 4.4\ \mu \mathrm{s}$ per token) on GPU, achieving a $100\times$ latency improvement over prior work."
}