Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

Open access
Liu, Peiyu, Liu, Zikang, Gao, Ze-Feng, Gao, Dawei, Zhao, Wayne Xin, Li, Yaliang, Ding, Bolin, Wen, Ji-Rong · 2024 · Proceedings of the Language Resources and Evaluation Conference

Abstract

Despite the superior performance, Large Language Models (LLMs) require significant computational resources for deployment and use.To overcome this issue, quantization methods have been widely applied to reduce the memory footprint of LLMs as well as increase the inference rate.However, a major challenge is that low-bit quantization methods often lead to performance degradation.It is important to understand how quantization impacts the capacity of LLMs.Different from previous studies focused on overall performance, this work aims to investigate the impact of quantization on emergent abilities, which are important characteristics that distinguish LLMs from small language models.Specifically, we examine the abilities of in-context learning, chain-of-thought reasoning, and instruction-following in quantized LLMs.Our empirical experiments show that these emergent abilities still exist in 4-bit quantization models, while 2-bit models encounter severe performance degradation on the test of these abilities.To improve the performance of low-bit models, we conduct two special experiments: (1) fine-gained impact analysis that studies which components (or substructures) are more sensitive to quantization, and (2) performance compensation through model fine-tuning.Our work derives a series of important findings to understand the impact of quantization on emergent abilities and sheds light on the possibilities of extremely low-bit quantization for LLMs.

Overview

Integrity signals

Registry

Crossref · 10.63317/5my4wtsi85on

Cites

0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

The publisher hasn’t deposited this paper’s reference list.

Cited by

See all 36

Metadata

Authors
Liu, P., Liu, Z., Gao, Z.-F., Gao, D., Zhao, W. X., Li, Y., Ding, B., & Wen, J.-R.
Affiliations
Renmin University of China (CN)
Venue
Proceedings of the Language Resources and Evaluation Conference
Published
2024-05
Pages
5174-5190
ISSN
2522-2686
OpenAlex
W7131783502
Cited by
3
References
0
Citations by year
2026: 2
FWCI
0.59
Type
conference paper
Language
en
Open access
Locations
  • Language Resources and Evaluation Conference (LREC) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Natural Science Foundation of China (62222215, 62206299)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
emergent capabilities, large language models, quantized models, model compression, quantization

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: Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study. https://app.cochat.ai/papers/10.63317/5my4wtsi85on
The paper
Liu, P., Liu, Z., Gao, Z.-F., Gao, D., Zhao, W. X., Li, Y., Ding, B., & Wen, J.-R. (2024). Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study. Proceedings of the Language Resources and Evaluation Conference. https://doi.org/10.63317/5my4wtsi85on

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.