Result Details

PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark

BELANEC, R.; PECHER, B.; SRBA, I.; BIELIKOVÁ, M. PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Morocco: Association for Computational Linguistics, 2026. p. 3035-3054. ISBN: 979-8-89176-380-7.
Type
conference paper
Language
English
Authors
Belanec Róbert, Bc., DCGM (FIT)
Pecher Branislav, Ing., Ph.D.
Srba Ivan, Ing., Ph.D.
Bieliková Mária, prof. Ing., Ph.D., DCGM (FIT)
Abstract

Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limiting their accessibility. Parameter-Efficient Fine-Tuning (PEFT) methods address this challenge by reducing the number of trainable parameters while maintaining strong downstream performance. Despite the advances in PEFT methods, current evaluations remain limited (in terms of evaluated models and datasets) and difficult to reproduce. To bridge this gap, we introduce PEFT-Bench, a unified end-to-end benchmark for evaluating diverse PEFT methods on autoregressive LLMs. We demonstrate its usage across 27 NLP datasets and 7 PEFT methods. To account for different PEFT training and inference factors, we also introduce the PEFT Soft Cost Penalties (PSCP) metric, which takes trainable parameters, inference speed, and training memory usage into account.

Keywords

parameter-efficient-training, LLM Efficiency, NLP in resource-constrained settings

URL
Published
2026
Pages
3035–3054
Proceedings
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
ISBN
979-8-89176-380-7
Publisher
Association for Computational Linguistics
Place
Morocco
DOI
BibTeX
@inproceedings{BUT200142,
  author="Róbert {Belanec} and Branislav {Pecher} and Ivan {Srba} and Mária {Bieliková}",
  title="PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark",
  booktitle="Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
  year="2026",
  pages="3035--3054",
  publisher="Association for Computational Linguistics",
  address="Morocco",
  doi="10.18653/v1/2026.eacl-long.140",
  isbn="979-8-89176-380-7",
  url="https://aclanthology.org/2026.eacl-long.140/"
}
Departments
Back to top