Image de couverture de livre

Lifelong Knowledge Editing requires Better Regularization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gupta, Akshat, Prateepamornkul, Phudish, Lu, Maochuan, Alaa, Ahmed, Hartvigsen, Thomas, Anumanchipalli, Gopala
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Knowledge Editing via Minimal Precomputation
par: Gupta, Akshat, et autres
Publié: (2025)

Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing
par: Gupta, Akshat, et autres
Publié: (2025)

Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
par: Yoon, Junsang, et autres
Publié: (2024)

A Unified Framework for Model Editing
par: Gupta, Akshat, et autres
Publié: (2024)

Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
par: Gupta, Akshat, et autres
Publié: (2024)

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
par: Gupta, Akshat, et autres
Publié: (2024)

Model Editing at Scale leads to Gradual and Catastrophic Forgetting
par: Gupta, Akshat, et autres
Publié: (2024)

Evolutionary Strategies lead to Catastrophic Forgetting in LLMs
par: Abdi, Immanuel, et autres
Publié: (2026)

Self-Assessment Tests are Unreliable Measures of LLM Personality
par: Gupta, Akshat, et autres
Publié: (2023)

FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
par: Mittu, Fazal, et autres
Publié: (2024)

How Do LLMs Use Their Depth?
par: Gupta, Akshat, et autres
Publié: (2025)

The Oracle Has Spoken: A Multi-Aspect Evaluation of Dialogue in Pythia
par: Chen, Zixun, et autres
Publié: (2025)

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
par: Thede, Lukas, et autres
Publié: (2025)

Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE
par: Lian, Jiachen, et autres
Publié: (2022)

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
par: Li, Jiaang, et autres
Publié: (2024)

KScope: A Framework for Characterizing the Knowledge Status of Language Models
par: Xiao, Yuxin, et autres
Publié: (2025)

PokerBench: Training Large Language Models to become Professional Poker Players
par: Zhuang, Richard, et autres
Publié: (2025)

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
par: Gu, Xiaojie, et autres
Publié: (2025)

Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding
par: Sun, Shenghuan, et autres
Publié: (2024)

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
par: Wang, Zhilin, et autres
Publié: (2025)

Model Merging for Knowledge Editing
par: Fu, Zichuan, et autres
Publié: (2025)

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
par: Wang, Peng, et autres
Publié: (2024)

Multi-hop Question Answering under Temporal Knowledge Editing
par: Cheng, Keyuan, et autres
Publié: (2024)

SAKE: Steering Activations for Knowledge Editing
par: Scialanga, Marco, et autres
Publié: (2025)

Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top
par: Cheng, Keyuan, et autres
Publié: (2024)

FLEKE: Federated Locate-then-Edit Knowledge Editing
par: Zhao, Zongkai, et autres
Publié: (2025)

Instruction-tuned Language Models are Better Knowledge Learners
par: Jiang, Zhengbao, et autres
Publié: (2024)

Sparse Autoencoder Features for Classifications and Transferability
par: Gallifant, Jack, et autres
Publié: (2025)

Identifying Multiple Personalities in Large Language Models with External Evaluation
par: Song, Xiaoyang, et autres
Publié: (2024)

COMPKE: Complex Question Answering under Knowledge Editing
par: Cheng, Keyuan, et autres
Publié: (2025)

Knowledge Editing on Black-box Large Language Models
par: Song, Xiaoshuai, et autres
Publié: (2024)

Time Sensitive Knowledge Editing through Efficient Finetuning
par: Ge, Xiou, et autres
Publié: (2024)

MemEIC: A Step Toward Continual and Compositional Knowledge Editing
par: Seong, Jin, et autres
Publié: (2025)

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
par: Zhang, Zhuoran, et autres
Publié: (2024)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
par: Veldanda, Akshaj Kumar, et autres
Publié: (2024)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
par: Shi, Yucheng, et autres
Publié: (2024)

MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
par: Li, Jiaqi, et autres
Publié: (2024)

Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
par: Zhou, Yueer, et autres
Publié: (2025)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
par: Ho, Matthew, et autres
Publié: (2025)

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
par: Wu, Chenyuan, et autres
Publié: (2024)