Journal article · 2026 · Open access
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
IEEE Access, 14, 96771–96793 · Published 1 January 2026 · DOI 10.1109/access.2026.3703899
In brief
“Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models” is a 2026 journal article by Artyom Kharinaev and 5 co-authors, published in IEEE Access. OpenAlex counts 26 citations as of 17 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Access.
- Citations
- 26
- Most cited in
- 2026 (23)
- Field-weighted impact
- 27.90
- References
- 68
- Authors
- 6
Abstract
Large Language Models (LLMs) are powerful tools for modern applications, but their computational demands limit accessibility. Quantization offers efficiency gains, yet its impact on safety and trustworthiness remains poorly understood. To address this, we introduce OpenSafetyMini, a human-curated safety dataset with 1,067 challenging questions to rigorously evaluate model behavior.We publicly release human safety evaluations for four LLMs (both quantized and full-precision), totaling 4,268 annotated question-answer pairsa. By assessing 66 quantized variants of these models using four post-training quantization (PTQ) and two quantization-aware training (QAT) methods across four safety benchmarks including human centric evaluations, we uncover critical safety performance trade offs. Our results show both PTQ and QAT can degrade safety alignment, with QAT techniques like QLORA or STE performing less safely. No single method consistently outperforms others across benchmarks, precision settings, or models, highlighting the need for safety-aware compression strategies. Furthermore, precision-specialized methods (e.g., QUIK/AWQ for 4-bit, AQLM/QUIP# for 2-bit) excel at their target precision, meaning that these methods are not superior compression methods but rather distinct approaches.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kharinaev, A., Moskvoretskii, V., Shvetsov, E., Studenikina, K. A., Bykov, M., & Burnaev, E. V. (2026). Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models. IEEE Access, 14, 96771–96793. https://doi.org/10.1109/access.2026.3703899
MLA 9
Kharinaev, Artyom, et al. “Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models.” IEEE Access, vol. 14, 2026, pp. 96771–96793. https://doi.org/10.1109/access.2026.3703899.
Chicago
Kharinaev, Artyom, Viktor Moskvoretskii, Egor Shvetsov, Kseniia A. Studenikina, Mikhail Bykov, and Evgeny Vladimirovich Burnaev. 2026. “Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models.” IEEE Access 14: 96771–96793. https://doi.org/10.1109/access.2026.3703899.
Harvard
Kharinaev, A. et al. (2026) ‘Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models’, IEEE Access, 14, pp. 96771–96793. doi:10.1109/access.2026.3703899.
IEEE
A. Kharinaev, V. Moskvoretskii, E. Shvetsov, K. A. Studenikina, M. Bykov, and E. V. Burnaev, “Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models,” IEEE Access, vol. 14, pp. 96771–96793, 2026, doi: 10.1109/access.2026.3703899.
BibTeX
@article{kharinaev2026investigating,
title = {{Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models}},
author = {Kharinaev, Artyom and Moskvoretskii, Viktor and Shvetsov, Egor and Studenikina, Kseniia A. and Bykov, Mikhail and Burnaev, Evgeny Vladimirovich},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {96771--96793},
doi = {10.1109/access.2026.3703899},
url = {https://doi.org/10.1109/access.2026.3703899}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- large language models
- model quantization
- reliability
- post-training quantization
- quantization-aware training
- QLoRA
- AWQ
- QUIP
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Kharinaev, A., Moskvoretskii, V., Shvetsov, E., Studenikina, K. A., Bykov, M., & Burnaev, E. V. (2026). Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models. IEEE Access, 14, 96771–96793. https://doi.org/10.1109/access.2026.3703899
How many times has this paper been cited?
26 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Access: sign in and open the full text from this page.
Who wrote this paper?
Artyom Kharinaev, Viktor Moskvoretskii, Egor Shvetsov, Kseniia A. Studenikina, Mikhail Bykov, Evgeny Vladimirovich Burnaev.
What is the DOI of this paper?
10.1109/access.2026.3703899, permanently at https://doi.org/10.1109/access.2026.3703899. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.