Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yao, Liang, Di, Peng, Minlong
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
par: Lin, Zekai, et autres
Publié: (2026)

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
par: Han, Xiaosong, et autres
Publié: (2026)

All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
par: Deshmukh, Advait, et autres
Publié: (2024)

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
par: Xue, Chao, et autres
Publié: (2026)

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

DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
par: Gao, Ziyuan, et autres
Publié: (2025)

Shall Your Data Strategy Work? Perform a Swift Study
par: Peng, Minlong, et autres
Publié: (2025)

DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
par: Liu, Xiaoyu, et autres
Publié: (2026)

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
par: Zhang, Dongxu, et autres
Publié: (2025)

Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
par: Yang, Sen, et autres
Publié: (2024)

TriAdaptLoRA: Brain-Inspired Triangular Adaptive Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
par: Liang, Yao, et autres
Publié: (2025)

Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation
par: Wu, Suhang, et autres
Publié: (2024)

Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes
par: Hacohen, Uri, et autres
Publié: (2024)

Not All Correct Answers Are Equal: Why Your Distillation Source Matters
par: Tian, Xiaoyu, et autres
Publié: (2025)

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
par: Gu, Naibin, et autres
Publié: (2024)

Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning
par: Liang, Yao, et autres
Publié: (2024)

Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
par: Lialin, Vladislav, et autres
Publié: (2023)

Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
par: Kim, JongWoo, et autres
Publié: (2024)

Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation
par: Su, Tong, et autres
Publié: (2024)

From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
par: Gong, Xuan, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
par: Gao, Ziqi, et autres
Publié: (2024)

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
par: Liu, Yongkang, et autres
Publié: (2026)

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
par: Gu, Naibin, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning With Adapters
par: Chen, Keyu, et autres
Publié: (2024)

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation
par: Pan, Ruotong, et autres
Publié: (2024)

Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
par: Wang, Ruoyu, et autres
Publié: (2024)

Boosting Large Language Models with Mask Fine-Tuning
par: Zhang, Mingyuan, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning for Foundation Models
par: Zhang, Dan, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning
par: Prottasha, Nusrat Jahan, et autres
Publié: (2024)

SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning
par: Wen, Zhihao, et autres
Publié: (2024)

All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations
par: Wanner, Miriam, et autres
Publié: (2025)

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
par: Lu, Xudong, et autres
Publié: (2024)

IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages
par: Khan, Mohammed Safi Ur Rahman, et autres
Publié: (2024)

Fine-Tuning Small Embeddings for Elevated Performance
par: Silwal, Biraj
Publié: (2024)

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
par: Petrov, Ivo, et autres
Publié: (2026)

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
par: Ye, Junjie, et autres
Publié: (2025)

The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities
par: Stap, David, et autres
Publié: (2024)

Parameter-Efficient Fine-Tuning via Circular Convolution
par: Chen, Aochuan, et autres
Publié: (2024)

Parameter-Efficient Fine-Tuning of State Space Models
par: Galim, Kevin, et autres
Publié: (2024)

PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
par: Belanec, Robert, et autres
Publié: (2025)