Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models
Title card · GETSECURE.ai
Local language models can save memory by storing weights in fewer bits, and they can reduce sensitivity to the order of answer options by averaging a few reorderings.
Excerpt from arXiv AI
GETSECURE.ai hasn't published its own summary of this story yet. The complete report is at arXiv AI:
arXiv AI. (2026, November 10). Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models. arXiv AI. https://arxiv.org/abs/2611.14413v1
