Imagen de Portada

Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Oguntade, Abass
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
por: Kim, JongWoo, et al.
Publicado: (2024)

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
por: Kuo, Hsun-Yu, et al.
Publicado: (2024)

Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models
por: Kaddour, Jean, et al.
Publicado: (2023)

Comparative Analysis of Different Efficient Fine Tuning Methods of Large Language Models (LLMs) in Low-Resource Setting
por: Srinivasan, Krishna Prasad Varadarajan, et al.
Publicado: (2024)

Medical Concept Normalization in a Low-Resource Setting
por: Patzelt, Tim
Publicado: (2024)

Mortgage Language Model: Domain-Adaptive Pretraining with Residual Instruction, Alignment Tuning, and Task-Specific Routing
por: Jain, Manish, et al.
Publicado: (2025)

RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings
por: Han, Wei, et al.
Publicado: (2026)

Towards Enhancing Health Coaching Dialogue in Low-Resource Settings
por: Zhou, Yue, et al.
Publicado: (2024)

GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings
por: Swapnil, Ismam Nur, et al.
Publicado: (2025)

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
por: Sedykh, Ivan, et al.
Publicado: (2026)

Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP
por: Visser, Ruan, et al.
Publicado: (2026)

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts
por: Somayajula, Sai Ashish, et al.
Publicado: (2024)

Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning
por: Khade, Omkar, et al.
Publicado: (2024)

LoQT: Low-Rank Adapters for Quantized Pretraining
por: Loeschcke, Sebastian, et al.
Publicado: (2024)

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
por: Wang, Yao, et al.
Publicado: (2025)

Joint Localization and Activation Editing for Low-Resource Fine-Tuning
por: Lai, Wen, et al.
Publicado: (2025)

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data
por: Ehab, Mohamed, et al.
Publicado: (2026)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
por: Zhao, Bowen, et al.
Publicado: (2024)

Language Models Improve When Pretraining Data Matches Target Tasks
por: Mizrahi, David, et al.
Publicado: (2025)

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
por: Grangier, David, et al.
Publicado: (2024)

How Does Code Pretraining Affect Language Model Task Performance?
por: Petty, Jackson, et al.
Publicado: (2024)

Not All LLM Reasoners Are Created Equal
por: Hosseini, Arian, et al.
Publicado: (2024)

Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs
por: Dong, Jiancheng, et al.
Publicado: (2024)

Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks
por: Seo, Minju, et al.
Publicado: (2024)

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
por: Lu, Xudong, et al.
Publicado: (2024)

Evaluating the Effectiveness of Data Augmentation for Emotion Classification in Low-Resource Settings
por: Arora, Aashish, et al.
Publicado: (2024)

Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
por: Riabi, Arij, et al.
Publicado: (2021)

Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
por: Zhang, Jiazheng, et al.
Publicado: (2026)

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
por: Mukherjee, Subhojyoti, et al.
Publicado: (2025)

Weight-Inherited Distillation for Task-Agnostic BERT Compression
por: Wu, Taiqiang, et al.
Publicado: (2023)

SOI Matters: Analyzing Multi-Setting Training Dynamics in Pretrained Language Models via Subsets of Interest
por: Vassef, Shayan, et al.
Publicado: (2025)

Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection
por: Kang, Jiawen, et al.
Publicado: (2024)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
por: Kunstner, Frederik, et al.
Publicado: (2024)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
por: Ju, Yiming, et al.
Publicado: (2024)

Train Once, Answer All: Many Pretraining Experiments for the Cost of One
por: Bordt, Sebastian, et al.
Publicado: (2025)

Fine Tuning Methods for Low-resource Languages
por: Bakkenes, Tim, et al.
Publicado: (2025)

QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources
por: Li, Zhikai, et al.
Publicado: (2023)

MAP: Revisiting Weight Decomposition for Low-Rank Adaptation
por: Si, Chongjie, et al.
Publicado: (2025)

PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression
por: Vicentino, Caio
Publicado: (2026)

MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions
por: Köksal, Abdullatif, et al.
Publicado: (2024)