---
title: "ARCQuant — paper by Meng et al. (2026) — summary and ideas"
description: "The paper tackles accuracy loss in 4-bit weight-and-activation (W4A4) post-training quantization of… 35 references, cited by 3 papers here."
authors: ["Haoqian Meng", "Yilun Luo", "Yafei Zhao", "Wenyuan Liu", "Peng Zhang", "Xindian Ma"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.388/"
doi: "10.18653/v1/2026.acl-long.388"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/meng-2026-arcquant-boosting-nvfp4-quantization-augmented/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/meng-2026-arcquant-boosting-nvfp4-quantization-augmented/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/) / ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

# ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

**Authors:** Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, [Peng Zhang](https://md.research.elamur.ai/free/en/authors/peng-zhang/) and Xindian Ma · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.388/) · [PDF](https://aclanthology.org/2026.acl-long.388.pdf) · [DOI 10.18653/v1/2026.acl-long.388](https://doi.org/10.18653/v1/2026.acl-long.388) · [OpenAlex](https://openalex.org/W7166887532)

**Citations:** 2 citations (OpenAlex, 2026-10-14) · 3 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper tackles accuracy loss in 4-bit weight-and-activation (W4A4) post-training quantization of LLMs in the NVFP4 format, which NVIDIA Blackwell GPUs support natively. Existing techniques fit NVFP4 poorly. Hadamard-style rotations spread outlier magnitudes into neighbouring blocks, which undermines NVFP4's 16-element block isolation. Mixed-precision schemes such as Atom need operands with different group sizes, which Tensor Core MMA instructions cannot process efficiently. ARCQuant takes a different route. Using calibration data, it reorders channels offline and picks the outlier channels whose values exceed a threshold. It then appends their quantized residuals to the activation matrix as extra channels, also in NVFP4. Because the error correction sits inside the reduction dimension of one matrix multiplication, standard optimized GEMM kernels can be used. The authors prove that this two-stage scheme has a worst-case error bound similar to MXFP8. On LLaMA and Qwen models, accuracy is close to FP16, with up to 3× speedup. This makes near-8-bit quality achievable on pure 4-bit hardware paths.

## Key points
- **Method**
  - Channels are sorted by absolute maximum, following Atom.
  - The outlier threshold is τ = 2⁻³·M, where M is the layer-wise maximum. The factor reflects the exponent-width gap between E5M2 and E2M1.
  - Weights are quantized with plain RTN.
- **Hardware results:** evaluated using two GPUs, the RTX 5090 and the RTX PRO 6000.
  - Up to 3× speedup over FP16.
  - On Qwen2.5-7B with batch size 8, decoding is 1.96× faster than FP16 at sequence length 1024 and 2.08× faster at 2048.
- **Scale and architecture:** gains over NVFP4+RTN hold beyond 7B/8B models.
  - On Llama 3.1-70B: +0.65 average zero-shot accuracy, −0.23 WikiText2 perplexity, +0.50 MMLU.
  - Improvements also appear on the MoE model Mixtral 8x7B-Instruct.
- **Robustness**
  - Changing the calibration set (WikiText2, C4, HumanEval) shifts perplexity by under 0.03.
  - Qwen2.5-Coder-7B-Instruct keeps over 99% of FP16 accuracy on coding benchmarks.
- **Other formats:** applied to INT4 on Llama 3.1-8B, ARCQuant lowers perplexity by 0.89 and raises zero-shot accuracy by 2.12%.
- **Code:** available at github.com/actypedef/ARCQuant.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tianjin University](https://md.research.elamur.ai/free/en/universities/tianjin-university/) — University, Tianjin, China · 41 works · 1,128 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 252 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 133 works · [⚙️ Electrical and Electronic Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/electrical-and-electronic-engineering/) · 18 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 242 works

## Cite

Cite as: Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang and Xindian Ma. 2026. ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{meng2026arcquant,
  title = {{ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs}},
  author = {Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang and Xindian Ma},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.388},
  url = {https://doi.org/10.18653/v1/2026.acl-long.388}
}
```

- [← previous A Study of LLMs' Preferences for Libraries and Programming Languages](https://md.research.elamur.ai/free/en/papers/twist-2026-study-llms-preferences-libraries-programming/)
- [next → Are Formal and Functional Linguistic Mechanisms Dissociated in Language Models?](https://md.research.elamur.ai/free/en/papers/hanna-2026-are-formal-functional-linguistic-mechanisms/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

35 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Saleh Ashkboos, Ilia Markov, Elias Frantar, Tingxuan Zhong, Xincheng Wang, Jie Ren, Torsten Hoefler, and Dan Alistarh. 2023. Quik: Towards end-to-end 4-bit inference on generative large language models. arXiv preprint arXiv:2310.09259. [find](https://scholar.google.com/scholar?q=Saleh+Ashkboos%2C+Ilia+Markov%2C+Elias+Frantar%2C+Tingxuan+Zhong%2C+Xincheng+Wang%2C+Jie+Ren%2C+Torsten+Hoefler%2C+and+Dan+Alistarh%2E+2023%2E+Quik%3A+Towards+end%2Dto%2Dend+4%2Dbit+inference+on+generative+large+language+model)
2. Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, and James Hensman. 2024. [Quarot: Outlier-free 4-bit inference in rotated LLMs](https://md.research.elamur.ai/free/en/papers/ashkboos-2024-quarot-outlier-free-4-bit/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
3. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
4. Bita Darvish Rouhani, Ritchie Zhao, Ankit More, Mathew Hall, Alireza Khodamoradi, Summer Deng, Dhruv Choudhary, Marius Cornea, Eric Dellinger, Kristof Denolf, Stosic Dusan, Venmugil Elango, Maximilian Golub, Alexander Heinecke, Phil James-Roxby, Dharmesh Jani, Gaurav Kolhe, Martin Lang-hammer, Ada L… [find](https://scholar.google.com/scholar?q=Bita+Darvish+Rouhani%2C+Ritchie+Zhao%2C+Ankit+More%2C+Mathew+Hall%2C+Alireza+Khodamoradi%2C+Summer+Deng%2C+Dhruv+Choudhary%2C+Marius+Cornea%2C+Eric+Dellinger%2C+Kristof+Denolf%2C+Stosic+Dusan%2C+Venmugil+Elango%2C+Maximilian)
5. Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. Llm.int8(): 8-bit matrix multiplication for transformers at scale. Preprint, arXiv:2208.07339. [find](https://scholar.google.com/scholar?q=Tim+Dettmers%2C+Mike+Lewis%2C+Younes+Belkada%2C+and+Luke+Zettlemoyer%2E+2022%2E+Llm%2Eint8%28%29%3A+8%2Dbit+matrix+multiplication+for+transformers+at+scale%2E+Preprint%2C+arXiv%3A2208%2E07339%2E)
6. Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. Gptq: Accurate post-training quantization for generative pre-trained transformers. Preprint, arXiv:2210.17323. [find](https://scholar.google.com/scholar?q=Elias+Frantar%2C+Saleh+Ashkboos%2C+Torsten+Hoefler%2C+and+Dan+Alistarh%2E+2023%2E+Gptq%3A+Accurate+post%2Dtraining+quantization+for+generative+pre%2Dtrained+transformers%2E+Preprint%2C+arXiv%3A2210%2E17323%2E)
7. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, and 5 others.… [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Jonathan+Tow%2C+Baber+Abbasi%2C+Stella+Biderman%2C+Sid+Black%2C+Anthony+DiPofi%2C+Charles+Foster%2C+Laurence+Golding%2C+Jeffrey+Hsu%2C+Alain+Le+Noac%E2%80%99h%2C+Haonan+Li%2C+Kyle+McDonell%2C+Niklas+Muennighoff%2C+Chris+Oci)
8. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, and et al. Akhil Mathur. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Preprint, arXiv:2407.21783.
9. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). Preprint, arXiv:2108.07732.
10. Ziyi Guan, Hantao Huang, Yupeng Su, Hong Huang, Ngai Wong, and Hao Yu. 2024. Aptq: Attention-aware post-training mixed-precision quantization for large language models. In Proceedings of the 61st ACM/IEEE Design Automation Conference, pages 1–6. [find](https://scholar.google.com/scholar?q=Ziyi+Guan%2C+Hantao+Huang%2C+Yupeng+Su%2C+Hong+Huang%2C+Ngai+Wong%2C+and+Hao+Yu%2E+2024%2E+Aptq%3A+Attention%2Daware+post%2Dtraining+mixed%2Dprecision+quantization+for+large+language+models%2E+In+Proceedings+of+the+61st+ACM%2F)
11. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
12. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Proceedings of the International Conference on Learning Representations (ICLR).
13. Brian Chmiel, Maxim Fishman, Ron Banner, and Daniel Soudry. 2025. Fp4 all the way: Fully quantized training of llms. arXiv preprint arXiv:2505.19115. — [arXiv:2505.19115](https://arxiv.org/abs/2505.19115) [find](https://scholar.google.com/scholar?q=Brian+Chmiel%2C+Maxim+Fishman%2C+Ron+Banner%2C+and+Daniel+Soudry%2E+2025%2E+Fp4+all+the+way%3A+Fully+quantized+training+of+llms%2E+arXiv+preprint+arXiv%3A2505%2E19115%2E+%E2%80%94+%5BarXiv%3A2505%2E19115%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E19)
14. Coleman Hooper, Charbel Sakr, Ben Keller, Rang-harajan Venkatesan, Kurt Keutzer, Sophia Shao, and Brucek Khailany. 2025. Fgmp: Fine-grained mixed-precision weight and activation quantization for hardware-accelerated llm inference. Preprint, arXiv:2504.14152. — [arXiv:2504.14152](https://arxiv.org/abs/2504.14152) [find](https://scholar.google.com/scholar?q=Coleman+Hooper%2C+Charbel+Sakr%2C+Ben+Keller%2C+Rang%2Dharajan+Venkatesan%2C+Kurt+Keutzer%2C+Sophia+Shao%2C+and+Brucek+Khailany%2E+2025%2E+Fgmp%3A+Fine%2Dgrained+mixed%2Dprecision+weight+and+activation+quantization+for+hardw)
15. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. [Think you have solved question answering? try arc, the ai2 reasoning challenge](https://md.research.elamur.ai/free/en/papers/clark-2018-think-have-solved-question-answering/). arXiv:1803.05457v1.
16. Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, and Song Han. 2024. Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models. arXiv preprint arXiv:2411.05007. [find](https://scholar.google.com/scholar?q=Muyang+Li%2C+Yujun+Lin%2C+Zhekai+Zhang%2C+Tianle+Cai%2C+Xiuyu+Li%2C+Junxian+Guo%2C+Enze+Xie%2C+Chenlin+Meng%2C+Jun%2DYan+Zhu%2C+and+Song+Han%2E+2024%2E+Svdquant%3A+Absorbing+outliers+by+low%2Drank+components+for+4%2Dbit+diffusion+)
17. Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for llm compression and acceleration. In MLSys. [find](https://scholar.google.com/scholar?q=Ji+Lin%2C+Jiaming+Tang%2C+Haotian+Tang%2C+Shang+Yang%2C+Wei%2DMing+Chen%2C+Wei%2DChen+Wang%2C+Guangxuan+Xiao%2C+Xingyu+Dang%2C+Chuang+Gan%2C+and+Song+Han%2E+2024%2E+Awq%3A+Activation%2Daware+weight+quantization+for+llm+compression)
18. Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, and Song Han. 2025. Qserve: W4a8kv4 quantization and system co-design for efficient llm serving. Preprint, arXiv:2405.04532. [find](https://scholar.google.com/scholar?q=Yujun+Lin%2C+Haotian+Tang%2C+Shang+Yang%2C+Zhekai+Zhang%2C+Guangxuan+Xiao%2C+Chuang+Gan%2C+and+Song+Han%2E+2025%2E+Qserve%3A+W4a8kv4+quantization+and+system+co%2Ddesign+for+efficient+llm+serving%2E+Preprint%2C+arXiv%3A2405%2E045)
19. Wenyuan Liu, Haoqian Meng, Yilun Luo, Peng Zhang, and Xindian Ma. 2025. Micromix: Efficient mixed-precision quantization with microscaling formats for large language models. arXiv preprint arXiv:2508.02343. [find](https://scholar.google.com/scholar?q=Wenyuan+Liu%2C+Haoqian+Meng%2C+Yilun+Luo%2C+Peng+Zhang%2C+and+Xindian+Ma%2E+2025%2E+Micromix%3A+Efficient+mixed%2Dprecision+quantization+with+microscaling+formats+for+large+language+models%2E+arXiv+preprint+arXiv%3A2508%2E)
20. Nicholas Lourie, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2021. Unicorn on rainbow: A universal commonsense reasoning model on a new multitask benchmark. Preprint, arXiv:2103.13009. [find](https://scholar.google.com/scholar?q=Nicholas+Lourie%2C+Ronan+Le+Bras%2C+Chandra+Bhagavatula%2C+and+Yejin+Choi%2E+2021%2E+Unicorn+on+rainbow%3A+A+universal+commonsense+reasoning+model+on+a+new+multitask+benchmark%2E+Preprint%2C+arXiv%3A2103%2E13009%2E)
21. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. [Pointer sentinel mixture models](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/). CoRR, abs/1609.07843.
22. Nvidia. 2024. Nvidia blackwell architecture technical brief. [find](https://scholar.google.com/scholar?q=Nvidia%2E+2024%2E+Nvidia+blackwell+architecture+technical+brief%2E)
23. NVIDIA Corporation. 2024. cuDNN Frontend API v1.14.0: Block-Scaling Operation. [https://docs.nvidia.com/deeplearning/cudnn/frontend/](https://docs.nvidia.com/deeplearning/cudnn/frontend/) v1.14.0/operations/BlockScaling.html. Accessed: 2025-09-16. [↗](https://docs.nvidia.com/deeplearning/cudnn/frontend/)
24. Denis Paperno, Germán Kruszewski, Angeliki Lazaridou, Ngoc Quan Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, and Raquel Fernandez. 2016. [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://md.research.elamur.ai/free/en/papers/paperno-2016-lambada-dataset-word-prediction-requiring/). In Proceedings of the 54th Annual Meeting of the Association fo…
25. Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, and Xin Wang. 2025. Resq: Mixed-precision quantization of large language models with low-rank residuals. Preprint, arXiv:2412.14363. — [arXiv:2412.14363](https://arxiv.org/abs/2412.14363) [find](https://scholar.google.com/scholar?q=Utkarsh+Saxena%2C+Sayeh+Sharify%2C+Kaushik+Roy%2C+and+Xin+Wang%2E+2025%2E+Resq%3A+Mixed%2Dprecision+quantization+of+large+language+models+with+low%2Drank+residuals%2E+Preprint%2C+arXiv%3A2412%2E14363%2E+%E2%80%94+%5BarXiv%3A2412%2E14363%5D%28ht)
26. Yuantian Shao, Peisong Wang, Yuanteng Chen, Chang Xu, Zhihui Wei, and Jian Cheng. 2025. Block rotation is all you need for mxfp4 quantization. arXiv preprint arXiv:2511.04214. — [arXiv:2511.04214](https://arxiv.org/abs/2511.04214) [find](https://scholar.google.com/scholar?q=Yuantian+Shao%2C+Peisong+Wang%2C+Yuanteng+Chen%2C+Chang+Xu%2C+Zhihui+Wei%2C+and+Jian+Cheng%2E+2025%2E+Block+rotation+is+all+you+need+for+mxfp4+quantization%2E+arXiv+preprint+arXiv%3A2511%2E04214%2E+%E2%80%94+%5BarXiv%3A2511%2E04214%5D%28htt)
27. Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang Zhao, Yuening Li, Jiaxin Hu, Xianzhi Yu, Lu Hou, Chun Yuan, Xin Jiang, Wulong Liu, and Jun Yao. 2025. Flatquant: Flatness matters for LLM quantization. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, Ju… [find](https://scholar.google.com/scholar?q=Yuxuan+Sun%2C+Ruikang+Liu%2C+Haoli+Bai%2C+Han+Bao%2C+Kang+Zhao%2C+Yuening+Li%2C+Jiaxin+Hu%2C+Xianzhi+Yu%2C+Lu+Hou%2C+Chun+Yuan%2C+Xin+Jiang%2C+Wulong+Liu%2C+and+Jun+Yao%2E+2025%2E+Flatquant%3A+Flatness+matters+for+LLM+quantization)
28. Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, and Christopher De Sa. 2024. [QuIP$\\\#$: Even better LLM quantization with hadamard incoherence and lattice codebooks](https://md.research.elamur.ai/free/en/papers/tseng-2024-quip-even-better-llm-quantization/). In Forty-first International Conference on Machine Learning.
29. Tianwen Wei, Jian Luan, Wei Liu, Shuang Dong, and Bin Wang. 2023. [Cmath: Can your language model pass chinese elementary school math test?](https://md.research.elamur.ai/free/en/papers/wei-2023-cmath-language-model-pass/) Preprint, arXiv:2306.16636.
30. Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2024. Smoothquant: Accurate and efficient post-training quantization for large language models. Preprint, arXiv:2211.10438. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Ji+Lin%2C+Mickael+Seznec%2C+Hao+Wu%2C+Julien+Demouth%2C+and+Song+Han%2E+2024%2E+Smoothquant%3A+Accurate+and+efficient+post%2Dtraining+quantization+for+large+language+models%2E+Preprint%2C+arXiv%3A2211%2E10438)
31. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830. [find](https://scholar.google.com/scholar?q=Rowan+Zellers%2C+Ari+Holtzman%2C+Yonatan+Bisk%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+2019%2E+Hellaswag%3A+Can+a+machine+really+finish+your+sentence%3F+arXiv+preprint+arXiv%3A1905%2E07830%2E)
32. Yilong Zhao, Chien-Yu Lin, Kan Zhu, Zihao Ye, Lequn Chen, Size Zheng, Luis Ceze, Arvind Krishnamurthy, Tianqi Chen, and Baris Kasikci. 2024. Atom: Low-bit quantization for efficient and accurate llm serving. In Proceedings of Machine Learning and Systems, volume 6, pages 196–209. [find](https://scholar.google.com/scholar?q=Yilong+Zhao%2C+Chien%2DYu+Lin%2C+Kan+Zhu%2C+Zihao+Ye%2C+Lequn+Chen%2C+Size+Zheng%2C+Luis+Ceze%2C+Arvind+Krishnamurthy%2C+Tianqi+Chen%2C+and+Baris+Kasikci%2E+2024%2E+Atom%3A+Low%2Dbit+quantization+for+efficient+and+accurate+llm+s)
33. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+)
34. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). CoRR, abs/1910.10683.
35. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2019. Winogrande: An adversarial winograd schema challenge at scale. Preprint, arXiv:1907.10641. [find](https://scholar.google.com/scholar?q=Keisuke+Sakaguchi%2C+Ronan+Le+Bras%2C+Chandra+Bhagavatula%2C+and+Yejin+Choi%2E+2019%2E+Winogrande%3A+An+adversarial+winograd+schema+challenge+at+scale%2E+Preprint%2C+arXiv%3A1907%2E10641%2E)

*Updated 31 October 2026*