stat.MLMay 28, 2025

Highly Efficient and Effective LLMs with Multi-Boolean Architectures

Authors: Ba-Hien Tran, Van Minh Nguyen

Organizations: Huawei Paris Research Center, Paris, France

Abstract

Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and training-aware methods, which depend on full-precision latent weights, adding complexity and limiting efficiency. We propose a novel framework that represents LLMs with multi-kernel Boolean parameters and, for the first time, enables direct finetuning LMMs in the Boolean domain, eliminating the need for latent weights. This enhances representational capacity and dramatically reduces complexity during both finetuning and inference. Extensive experiments across diverse LLMs show our method outperforms recent ultra low-bit quantization and binarization techniques.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation

    Apr 21, 2026Siqing Song, Chuang Wang, Yong Lang +2LLM QuantizationActivation Quantization

  2. All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs

    Sep 5, 2026Zhixiong Zhao, Zukang Xu, Guangyu Sun +2LLM QuantizationPost-Training Quantization

  3. TernaryLLM: Ternarized Large Language Model

    Jun 11, 2024Tianqi Chen, Zhe Li, Weixiang Xu +6LLM QuantizationTernary Quantization