Imagen de Portada

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Ke, Qin, Yiming, Dimitriadis, Nikolaos, Favero, Alessandro, Frossard, Pascal
Formato:	Preprint
Publicado:	2025
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

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
por: Wang, Ke, et al.
Publicado: (2024)

Localizing Task Information for Improved Model Merging and Compression
por: Wang, Ke, et al.
Publicado: (2024)

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
por: Dimitriadis, Nikolaos, et al.
Publicado: (2024)

Model soups need only one ingredient
por: Abdollahpoorrostam, Alireza, et al.
Publicado: (2026)

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

Task Addition and Weight Disentanglement in Closed-Vocabulary Models
por: Hazimeh, Adam, et al.
Publicado: (2025)

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
por: Liu, Jinzhe, et al.
Publicado: (2025)

Minimal-Intervention KV Retention via Set-Conditioned Diversity
por: Sun, Libo, et al.
Publicado: (2026)

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

Backdoor Unlearning by Linear Task Decomposition
por: Abdelraheem, Amel, et al.
Publicado: (2025)

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

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

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
por: Qin, Haotong, et al.
Publicado: (2024)

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
por: Wang, Yue, et al.
Publicado: (2025)

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

Sparse Training of Discrete Diffusion Models for Graph Generation
por: Qin, Yiming, et al.
Publicado: (2023)

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
por: Favero, Alessandro, et al.
Publicado: (2025)

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

Lifelong Safety Alignment for Language Models
por: Wang, Haoyu, et al.
Publicado: (2025)

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
por: Wang, Peng, et al.
Publicado: (2024)

Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning
por: Giraldo, Juan Garcia, et al.
Publicado: (2025)

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
por: Bakman, Yavuz Faruk, et al.
Publicado: (2024)

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

Towards Lifelong Learning of Large Language Models: A Survey
por: Zheng, Junhao, et al.
Publicado: (2024)

Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
por: Nguyen, Duy, et al.
Publicado: (2026)

Sinkhorn Distance Minimization for Knowledge Distillation
por: Cui, Xiao, et al.
Publicado: (2024)

Time Is Effort: Estimating Human Post-Editing Time for Grammar Error Correction Tool Evaluation
por: Vadehra, Ankit, et al.
Publicado: (2025)

DeFoG: Discrete Flow Matching for Graph Generation
por: Qin, Yiming, et al.
Publicado: (2024)

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
por: He, Jinghan, et al.
Publicado: (2024)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
por: Ho, Matthew, et al.
Publicado: (2025)

Editing Arbitrary Propositions in LLMs without Subject Labels
por: Feigenbaum, Itai, et al.
Publicado: (2024)

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
por: Li, Junsong, et al.
Publicado: (2025)

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
por: Dong, Zilu, et al.
Publicado: (2025)

Few-shot Personalization of LLMs with Mis-aligned Responses
por: Kim, Jaehyung, et al.
Publicado: (2024)

Robust and Scalable Model Editing for Large Language Models
por: Chen, Yingfa, et al.
Publicado: (2024)

Balancing Symmetry and Efficiency in Graph Flow Matching
por: Honoré, Benjamin, et al.
Publicado: (2026)

Active Continual Learning: On Balancing Knowledge Retention and Learnability
por: Vu, Thuy-Trang, et al.
Publicado: (2023)

MiniDisc: Minimal Distillation Schedule for Language Model Compression
por: Zhang, Chen, et al.
Publicado: (2022)

Model Merging for Knowledge Editing
por: Fu, Zichuan, et al.
Publicado: (2025)

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
por: Wei, Zhepei, et al.
Publicado: (2026)