Pith. sign in

REVIEW 10 cited by

PB-LLM: Partially Binarized Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2310.00034 v2 pith:BVXQBROP submitted 2023-09-29 cs.LG cs.AIcs.CL

Yuzhang Shang , Zhihang Yuan , Qiang Wu , Zhen Dong This is my paper · ORCID
classification cs.LGcs.AIcs.CL
keywords binarizationllmspb-llmquantizationweightslow-bitbinarizedquantized
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collapsing LLMs, we propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs. Specifically, our exploration first uncovers the ineffectiveness of naive applications of existing binarization algorithms and highlights the imperative role of salient weights in achieving low-bit quantization. Thus, PB-LLM filters a small ratio of salient weights during binarization, allocating them to higher-bit storage, i.e., partially-binarization. PB-LLM is extended to recover the capacities of quantized LMMs, by analyzing from the perspective of post-training quantization (PTQ) and quantization-aware training (QAT). Under PTQ, combining the concepts from GPTQ, we reconstruct the binarized weight matrix guided by the Hessian matrix and successfully recover the reasoning capacity of PB-LLM in low-bit. Under QAT, we freeze the salient weights during training, explore the derivation of optimal scaling factors crucial for minimizing the quantization error, and propose a scaling mechanism based on this derived scaling strategy for residual binarized weights. Those explorations and the developed methodologies significantly contribute to rejuvenating the performance of low-bit quantized LLMs and present substantial advancements in the field of network binarization for LLMs.The code is available at https://github.com/hahnyuan/BinaryLLM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization

    quant-ph 2026-08 conditional novelty 6.0 of 10

    Quantum random-access codes let a one-qubit-per-weight quantizer retrieve context-dependent signs, strictly improving reconstruction risk over shared-sign one-bit PTQ when context-wise optimal signs disagree.

  2. Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Q-resafe restores much of the safety lost in quantized LLMs by distilling the original model's responses through DPO while selectively updating only safety-critical weights.

  3. Irrational Complex Rotations Empower Low-bit Optimizers

    cs.LG 2025-01 reject novelty 6.0 of 10

    π-Quant's core representation theorem fails: the curve e^{iθ}+e^{iπθ} is dense in the disk but does not cover it, and Lemma 3.2's angle formulas are internally inconsistent.

  4. DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A training-free two-stage token compression method speeds up video language model inference by about 1.5x and cuts memory use, while keeping accuracy close to the uncompressed model.

  5. Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Across four NAS/DNN-predictor regression benchmarks, GEN (deep graph convolution) achieves the best average rank over 11 GNN message-passing layers, though attention GATv2 wins on the largest graphs.

  6. Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

    cs.AI 2025-05 conditional novelty 5.0 of 10

    A task-oriented semantic communication framework for LLaVA-based vehicle assistants that crops image slices matched to the user's question and allocates transmission power by fused objective and subjective attention, ...

  7. FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs

    cs.LG 2025-04 conditional novelty 5.0 of 10

    FineQ quantizes LLM weights to 2.33 bits by protecting outliers inside 3-weight clusters and adds a temporal-coding accelerator that replaces multipliers with adders.

  8. Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Squeeze10-LLM is a staged mixed-precision post-training quantization method that binarizes 80% of LLM weights, keeps 20% at 4 bits, and reports strong sub-2-bit accuracy gains over PB-LLM.

  9. freePruner: A Training-free Approach for Large Multimodal Model Acceleration

    cs.CV 2024-11 conditional novelty 3.0 of 10

    freePruner selects 50 percent of visual tokens using attention-based importance and keeps accuracy close to the original model, enabling a training-free about 2x acceleration for LMMs.

  10. Resource-Efficient Language Models: Quantization for Fast and Accessible Inference

    cs.AI 2025-05 unverdicted

    A survey of post-training quantization techniques for large language models, covering schemes, granularities, and popular methods, with no new experimental results.

Pith tools