Imagen de Portada

Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Bowen, Wang, Meiyi, Soh, Harold
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction
por: Zhang, Bowen, et al.
Publicado: (2024)

Rethinking Data Selection at Scale: Random Selection is Almost All You Need
por: Xia, Tingyu, et al.
Publicado: (2024)

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
por: Gan, Chunjing, et al.
Publicado: (2024)

Not All Documents Are What You Need for Extracting Instruction Tuning Data
por: Zhang, Chi, et al.
Publicado: (2025)

Higher Layers Need More LoRA Experts
por: Gao, Chongyang, et al.
Publicado: (2024)

Discovering Significant Topics from Legal Decisions with Selective Inference
por: Soh, Jerrold
Publicado: (2024)

Not All Layers of LLMs Are Necessary During Inference
por: Fan, Siqi, et al.
Publicado: (2024)

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
por: Song, Feifan, et al.
Publicado: (2024)

Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models
por: Zhang, Yukun, et al.
Publicado: (2025)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
por: Taniguchi, Rei, et al.
Publicado: (2026)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
por: Djuhera, Aladin, et al.
Publicado: (2025)

GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
por: Huang, Wei, et al.
Publicado: (2026)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
por: Liu, Danni, et al.
Publicado: (2025)

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
por: Kamigaito, Hidetaka, et al.
Publicado: (2025)

All You Need is One: Capsule Prompt Tuning with a Single Vector
por: Liu, Yiyang, et al.
Publicado: (2025)

Distilling to Hybrid Attention Models via KL-Guided Layer Selection
por: Li, Yanhong, et al.
Publicado: (2025)

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
por: Wang, Xintong, et al.
Publicado: (2024)

AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages
por: Bakos, Steve, et al.
Publicado: (2025)

Contrast Is All You Need
por: Kilic, Burak, et al.
Publicado: (2023)

Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
por: Dong, Zhijin
Publicado: (2025)

Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders
por: Nadipalli, Suneel
Publicado: (2025)

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
por: Chekalina, Viktoriia, et al.
Publicado: (2024)

An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits
por: Steinmetz, Cody, et al.
Publicado: (2025)

Understanding Layer Significance in LLM Alignment
por: Shi, Guangyuan, et al.
Publicado: (2024)

Training on the Benchmark Is Not All You Need
por: Ni, Shiwen, et al.
Publicado: (2024)

Memory Layers at Scale
por: Berges, Vincent-Pierre, et al.
Publicado: (2024)

Adaptive Layer-skipping in Pre-trained LLMs
por: Luo, Xuan, et al.
Publicado: (2025)

LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?
por: Tamo, J. Ben, et al.
Publicado: (2026)

Agents Are All You Need for LLM Unlearning
por: Sanyal, Debdeep, et al.
Publicado: (2025)

All-in-One Tuning and Structural Pruning for Domain-Specific LLMs
por: Lu, Lei, et al.
Publicado: (2024)

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
por: Bai, Yuelin, et al.
Publicado: (2024)

Prediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing
por: Cong, Peizhuang, et al.
Publicado: (2024)

More Agents Is All You Need
por: Li, Junyou, et al.
Publicado: (2024)

Rho-1: Not All Tokens Are What You Need
por: Lin, Zhenghao, et al.
Publicado: (2024)

K-ON: Stacking Knowledge On the Head Layer of Large Language Model
por: Guo, Lingbing, et al.
Publicado: (2025)

Hallucination Detection with the Internal Layers of LLMs
por: Preiß, Martin
Publicado: (2025)

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
por: Askari, Hadi, et al.
Publicado: (2025)

Language is All a Graph Needs
por: Ye, Ruosong, et al.
Publicado: (2023)

Layer by Layer: Uncovering Hidden Representations in Language Models
por: Skean, Oscar, et al.
Publicado: (2025)

Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
por: Lu, Xiaoding, et al.
Publicado: (2024)