Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
Post-training quantization (PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations.We observe that these outliers are concentrated in specific channels and are asymmetric across channels.To address this issue, we propose the Outlier Suppression+ (OS+) framework, which contains the channel-wise shifting for asymmetry and channel-wise scaling for concentration.We show that these operations can be seamlessly migrated into subsequent modules while maintaining equivalence.Second, we propose a fast and stable scheme to calculate effective shifting and scaling values.The channel-wise shifting aligns the center of each channel for removal of outlier asymmetry.The channel-wise scaling quantitatively evaluates changes brought by migration and quantization for better quantization burden balance.We validate our OS+ under both standard and fine-grained quantization settings with models including BERT, OPT, BLOOM, BLOOMZ, and LLaMA.Comprehensive results across various tasks demonstrate the superiority of our approach.Especially, with standard quantization, OS+ can achieve near-floating-point performance on both small models and large language models on 8-bit and 6-bit.Besides, we establish a new state-of-the-art for 4-bit BERT with 15.5% improvement.Our code is available at https://github.com/ModelTC/ Outlier_Suppression_Plus.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453 · cited 2×
“In this section, we provide detailed descriptions of our implementation with the core part distilled in algorithm 1.”
MethodSelf-citationHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Neural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
PACT: Parameterized Clipping Activation for Quantized Neural Networks
Choi, J., Wang, Z., Venkataramani, S., Chuang, P. I.-J., Srinivasan, V., & Gopalakrishnan, K. (2018) · arXiv · doi:10.48550/arxiv.1805.06085 · Cited by 703
Cited by
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2023) · arXiv · doi:10.48550/arxiv.2307.06435 · Cited by 1,259
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration
Lin, J., Tang, J., Tang, H., Yang, S., Xiao, G., & Han, S. (2025) · GetMobile: Mobile Computing and Communications · doi:10.1145/3714983.3714987 · Cited by 274
A Survey on Model Compression for Large Language Models
Zhu, X., Li, J., Liu, Y., Ma, C., & Wang, W. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00704 · Cited by 273
A survey of low-bit large language models: Basics, systems, and algorithms
Gong, R., Ding, Y., Wang, Z., Lv, C., Zheng, X., Du, J., Yong, Y., Gu, S., Qin, H., Guo, J., et al. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107856 · Cited by 16
Self-citation
Metadata
- Authors
- Wei, X., Zhang, Y., Li, Y., Zhang, X., Gong, R., Guo, J., & Liu, X.
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 1648-1665
- OpenAlex
- W4389524393
- Cited by
- 49
- References
- 37
- FWCI
- 5.57
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling. https://app.cochat.ai/papers/10.18653/v1/2023.emnlp-main.102
- The paper
- Wei, X., Zhang, Y., Li, Y., Zhang, X., Gong, R., Guo, J., & Liu, X. (2023). Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2023.emnlp-main.102
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.