English

The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)

Machine Learning 2025-08-11 v1

Abstract

Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of a fixed overall resource budget, a very different perspective arises. We introduce Signed-Zero Ternary (SZT), a 2-bit quantization that deterministically provides gradient information with no forward-path penalty. Our analysis provides evidence that it may improve information density compared to non-quantized alternatives.

Cite

@article{arxiv.2508.05905,
  title  = {The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)},
  author = {Jeffrey Uhlmann},
  journal= {arXiv preprint arXiv:2508.05905},
  year   = {2025}
}
R2 v1 2026-07-01T04:40:06.342Z