Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Methods of Medium Optimization01:28

Methods of Medium Optimization

70
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...
70

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A nanozyme-engineered implant surface for sequential photodynamic antibacterial and cytoprotective functions.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Navigating diagnosis: UK informal caregivers' experiences of the dementia assessment journey.

Aging & mental health·2026
Same author

Unlocking an Efficient SOD-to-CAT Catalytic Relay in a MOF Nanozyme via Dopamine-Driven Interfacial Nanoreconstruction for Osteoarthritis Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Injectable curdlan-derived hydrogel with differential release of copper and zinc ions for synergistic therapy of infected wounds.

Carbohydrate polymers·2026
Same author

A 3D-Printed Composite Hydrogel Engineered with a Coordination-Reprogrammed Nanozyme for Synergistic Chemo-Physical Bone Therapy.

ACS applied materials & interfaces·2026
Same author

Unveiling causal relationships between inflammatory cytokines and neurite orientation dispersion and density imaging phenotypes: Insights from bidirectional Mendelian randomization and bibliometric analysis.

Psychiatry and clinical neurosciences·2026
Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026
Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026
Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026
Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026
Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026
Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026
See all related articles

Related Experiment Video

Updated: May 3, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K

Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article

Olesya Razuvayevskaya1, Ben Wu1, João A Leite1

  • 1Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom.

Plos One
|May 3, 2024
PubMed
Summary
This summary is machine-generated.

Parameter-efficient fine-tuning techniques like Adapters and Low-Rank Adaptation (LoRA) offer efficient language model training. This study shows their effectiveness in multilingual text classification, even with limited data.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

524
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

548

Related Experiment Videos

Last Updated: May 3, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

524
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

548

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Computational Linguistics

Background:

  • Parameter-efficient fine-tuning (PEFT) methods, including Adapters and Low-Rank Adaptation (LoRA), enhance language model training efficiency.
  • Prior research suggests PEFT can improve performance on specific classification tasks.
  • This study expands on existing work by evaluating PEFT's impact on classification performance and computational costs relative to full fine-tuning.

Purpose of the Study:

  • To investigate the influence of Adapters and LoRA on multilingual text classification performance and computational costs.
  • To analyze the efficacy of PEFT across various multilingual text classification tasks, including genre, framing, and persuasion detection.
  • To assess PEFT's performance under different training scenarios (original multilingual data, English translations, English-only subsets) and across diverse languages, especially for tasks with limited training data.

Main Methods:

  • Comparative analysis of parameter-efficient fine-tuning (PEFT) techniques (Adapters, LoRA) against full fine-tuning.
  • Evaluation on multilingual text classification tasks with varying input lengths, class numbers, and difficulty levels.
  • In-depth analysis of PEFT performance across different training data configurations and languages.

Main Results:

  • Parameter-efficient fine-tuning techniques demonstrate competitive performance and efficiency in multilingual text classification.
  • Findings highlight the applicability of PEFT for multilabel classification and non-parallel multilingual tasks.
  • Efficacy varies based on training data scenarios and specific languages, offering nuanced insights.

Conclusions:

  • Adapters and LoRA are viable and efficient alternatives to full fine-tuning for many multilingual text classification scenarios.
  • These techniques are particularly beneficial for tasks involving varied input lengths and limited data.
  • The study provides practical guidance on applying PEFT in diverse multilingual NLP research and applications.