@inproceedings{lian-etal-2026-quantization,
    title = "Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models",
    author = "Lian, Xinyu  and
      Krichene, Walid  and
      Huang, Beichen  and
      Tanaka, Masahiro  and
      Ruwase, Olatunji  and
      Zhang, Li  and
      Zhang, Minjia",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2059/",
    pages = "46880--46894",
    ISBN = "979-8-89176-459-0"
}