Imagen de Portada

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yao, Liang, Di, Peng, Minlong
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
por: Lin, Zekai, et al.
Publicado: (2026)

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
por: Han, Xiaosong, et al.
Publicado: (2026)

All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
por: Deshmukh, Advait, et al.
Publicado: (2024)

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
por: Xue, Chao, et al.
Publicado: (2026)

Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings
por: Oguntade, Abass
Publicado: (2026)

DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
por: Gao, Ziyuan, et al.
Publicado: (2025)

Shall Your Data Strategy Work? Perform a Swift Study
por: Peng, Minlong, et al.
Publicado: (2025)

DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
por: Liu, Xiaoyu, et al.
Publicado: (2026)

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
por: Zhang, Dongxu, et al.
Publicado: (2025)

Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
por: Yang, Sen, et al.
Publicado: (2024)

TriAdaptLoRA: Brain-Inspired Triangular Adaptive Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
por: Liang, Yao, et al.
Publicado: (2025)

Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation
por: Wu, Suhang, et al.
Publicado: (2024)

Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes
por: Hacohen, Uri, et al.
Publicado: (2024)

Not All Correct Answers Are Equal: Why Your Distillation Source Matters
por: Tian, Xiaoyu, et al.
Publicado: (2025)

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
por: Gu, Naibin, et al.
Publicado: (2024)

Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning
por: Liang, Yao, et al.
Publicado: (2024)

Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
por: Lialin, Vladislav, et al.
Publicado: (2023)

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

Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
por: Su, Tong, et al.
Publicado: (2024)

From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
por: Gong, Xuan, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
por: Gao, Ziqi, et al.
Publicado: (2024)

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
por: Liu, Yongkang, et al.
Publicado: (2026)

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
por: Gu, Naibin, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning With Adapters
por: Chen, Keyu, et al.
Publicado: (2024)

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation
por: Pan, Ruotong, et al.
Publicado: (2024)

Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
por: Wang, Ruoyu, et al.
Publicado: (2024)

Boosting Large Language Models with Mask Fine-Tuning
por: Zhang, Mingyuan, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning for Foundation Models
por: Zhang, Dan, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning
por: Prottasha, Nusrat Jahan, et al.
Publicado: (2024)

SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning
por: Wen, Zhihao, et al.
Publicado: (2024)

All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations
por: Wanner, Miriam, et al.
Publicado: (2025)

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
por: Lu, Xudong, et al.
Publicado: (2024)

IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages
por: Khan, Mohammed Safi Ur Rahman, et al.
Publicado: (2024)

Fine-Tuning Small Embeddings for Elevated Performance
por: Silwal, Biraj
Publicado: (2024)

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
por: Petrov, Ivo, et al.
Publicado: (2026)

The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities
por: Stap, David, et al.
Publicado: (2024)

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
por: Ye, Junjie, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning via Circular Convolution
por: Chen, Aochuan, et al.
Publicado: (2024)

Parameter-Efficient Fine-Tuning of State Space Models
por: Galim, Kevin, et al.
Publicado: (2024)

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