Cover Image

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Jinzhe, Sun, Junshu, Shen, Shufan, Yang, Chenxue, Wang, Shuhui
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Scalable Graph Compressed Convolutions
by: Sun, Junshu, et al.
Published: (2024)

Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models
by: Shen, Shufan, et al.
Published: (2025)

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
by: Thede, Lukas, et al.
Published: (2025)

Towards Dynamic Message Passing on Graphs
by: Sun, Junshu, et al.
Published: (2024)

More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
by: Ma, Xin, et al.
Published: (2026)

Expanding Sparse Tuning for Low Memory Usage
by: Shen, Shufan, et al.
Published: (2024)

Relieving the Over-Aggregating Effect in Graph Transformers
by: Sun, Junshu, et al.
Published: (2025)

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
by: Shen, Shufan, et al.
Published: (2025)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
by: Dang, Tiantian, et al.
Published: (2026)

Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
by: Zhuang, Xialie, et al.
Published: (2025)

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
by: Gu, Xiaojie, et al.
Published: (2025)

Supernova: Achieving More with Less in Transformer Architectures
by: Tanase, Andrei-Valentin, et al.
Published: (2025)

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
by: Wang, Ke, et al.
Published: (2025)

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
by: Shen, Shufan, et al.
Published: (2025)

Lifelong Knowledge Editing requires Better Regularization
by: Gupta, Akshat, et al.
Published: (2025)

FLEKE: Federated Locate-then-Edit Knowledge Editing
by: Zhao, Zongkai, et al.
Published: (2025)

HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
by: Zeng, Yiming, et al.
Published: (2025)

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
by: Lyu, Sicheng, et al.
Published: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
by: Wu, Yuyang, et al.
Published: (2025)

Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers
by: Lou, Chao, et al.
Published: (2024)

Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
by: Zheng, Yilun, et al.
Published: (2025)

Trainable Dynamic Mask Sparse Attention
by: Shi, Jingze, et al.
Published: (2025)

MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models
by: Zhang, Ying, et al.
Published: (2024)

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
by: Liu, Hongyi, et al.
Published: (2025)

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
by: Zhang, Ningyu, et al.
Published: (2024)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
by: Christopoulou, Fenia, et al.
Published: (2024)

Persuasion Tokens for Editing Factual Knowledge in LLMs
by: Youssef, Paul, et al.
Published: (2026)

LIMR: Less is More for RL Scaling
by: Li, Xuefeng, et al.
Published: (2025)

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs
by: Zhang, Yifei, et al.
Published: (2024)

CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs
by: Fang, Jizhan, et al.
Published: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
by: Sun, Chung-En, et al.
Published: (2025)

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
by: Li, Jiaang, et al.
Published: (2024)

Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing
by: Baghel, Bhiman Kumar, et al.
Published: (2025)

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs
by: Lu, Zhenyan, et al.
Published: (2025)

MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
by: Wen, Shengtao, et al.
Published: (2025)

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
by: Liu, Yibai, et al.
Published: (2025)

Two-stage LLM Fine-tuning with Less Specialization and More Generalization
by: Wang, Yihan, et al.
Published: (2022)

Less is More for Improving Automatic Evaluation of Factual Consistency
by: Wang, Tong, et al.
Published: (2024)

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning
by: Wang, Yangfan, et al.
Published: (2026)

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
by: Hathidara, Ashutosh, et al.
Published: (2025)