Pith. sign in

REVIEW 1 cited by

Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.12311 v2 pith:P3WTIWYC submitted 2024-06-18 cs.LG

classification cs.LG
keywords binarizationbinarymosbinarylanguagellmsmethodsscalingtechniques
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Binarization, which converts weight parameters to binary values, has emerged as an effective strategy to reduce the size of large language models (LLMs). However, typical binarization techniques significantly diminish linguistic effectiveness of LLMs. To address this issue, we introduce a novel binarization technique called Mixture of Scales (BinaryMoS). Unlike conventional methods, BinaryMoS employs multiple scaling experts for binary weights, dynamically merging these experts for each token to adaptively generate scaling factors. This token-adaptive approach boosts the representational power of binarized LLMs by enabling contextual adjustments to the values of binary weights. Moreover, because this adaptive process only involves the scaling factors rather than the entire weight matrix, BinaryMoS maintains compression efficiency similar to traditional static binarization methods. Our experimental results reveal that BinaryMoS surpasses conventional binarization techniques in various natural language processing tasks and even outperforms 2-bit quantization methods, all while maintaining similar model size to static binarization techniques.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings

    cs.CL 2025-07 reject novelty 4.0 of 10

    Per-feature coordinate-search thresholds for binarizing BERT embeddings outperform fixed-threshold methods and occasionally match full-precision accuracy.

Pith tools