Cover Image

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pecher, Branislav, Cegin, Jan, Belanec, Robert, Simko, Jakub, Srba, Ivan, Bielikova, Maria
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
by: Pecher, Branislav, et al.
Published: (2026)

PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
by: Belanec, Robert, et al.
Published: (2025)

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
by: Cegin, Jan, et al.
Published: (2024)

RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
by: Cegin, Jan, et al.
Published: (2025)

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
by: Cegin, Jan, et al.
Published: (2024)

A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness
by: Pecher, Branislav, et al.
Published: (2023)

On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices
by: Pecher, Branislav, et al.
Published: (2024)

PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
by: Belanec, Robert, et al.
Published: (2025)

Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
by: Pecher, Branislav, et al.
Published: (2026)

Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance
by: Pecher, Branislav, et al.
Published: (2024)

Automatic Combination of Sample Selection Strategies for Few-Shot Learning
by: Pecher, Branislav, et al.
Published: (2024)

Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
by: Belanec, Robert, et al.
Published: (2024)

MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models
by: Hyben, Martin, et al.
Published: (2026)

LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?
by: Cegin, Jan, et al.
Published: (2024)

KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
by: Hromadka, Timo, et al.
Published: (2023)

A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages
by: Anikina, Tatiana, et al.
Published: (2025)

Multilingual and Multi-topical Benchmark of Fine-tuned Language models and Large Language Models for Check-Worthy Claim Detection
by: Hyben, Martin, et al.
Published: (2023)

Autonomation, Not Automation: Activities and Needs of European Fact-checkers as a Basis for Designing Human-Centered AI Systems
by: Hrckova, Andrea, et al.
Published: (2022)

Multilingual Previously Fact-Checked Claim Retrieval
by: Pikuliak, Matúš, et al.
Published: (2023)

Authorship Obfuscation in Multilingual Machine-Generated Text Detection
by: Macko, Dominik, et al.
Published: (2024)

Disinformation Capabilities of Large Language Models
by: Vykopal, Ivan, et al.
Published: (2023)

MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
by: Macko, Dominik, et al.
Published: (2023)

Beyond the Checkbox: Strengthening DSA Compliance Through Social Media Algorithmic Auditing
by: Solarova, Sara, et al.
Published: (2026)

Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors
by: Macko, Dominik, et al.
Published: (2025)

MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts
by: Macko, Dominik, et al.
Published: (2024)

Political Leaning and Politicalness Classification of Texts
by: Volf, Matous, et al.
Published: (2025)

A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages
by: Vykopal, Ivan, et al.
Published: (2025)

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
by: Pandey, Punya Syon, et al.
Published: (2025)

mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection
by: Macko, Dominik, et al.
Published: (2026)

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
by: Hameed, Marawan Gamal Abdel, et al.
Published: (2024)

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
by: Alajrami, Ahmed, et al.
Published: (2025)

Interpretable Predictability-Based AI Text Detection: A Replication Study
by: Skurla, Adam, et al.
Published: (2026)

mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
by: Skurla, Adam, et al.
Published: (2026)

SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
by: Peng, Qiwei, et al.
Published: (2025)

Revisiting Algorithmic Audits of TikTok: Poor Reproducibility and Short-term Validity of Findings
by: Mosnar, Matej, et al.
Published: (2025)

Soft Language Prompts for Language Transfer
by: Vykopal, Ivan, et al.
Published: (2024)

Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation
by: Zugecova, Aneta, et al.
Published: (2024)

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
by: Du, Yanrui, et al.
Published: (2024)

Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate
by: Pecher, Tom
Published: (2026)

Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models
by: Bui, Nghia, et al.
Published: (2025)