Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Chi, Zhang, Mengqi, Ye, Xiaotian, Cheng, Runxi, Zhou, Zisheng, Zhou, Ying, Ren, Pengjie, Chen, Zhumin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Uncovering Context Reliance in Unstructured Knowledge Editing
di: Zhou, Zisheng, et al.
Pubblicazione: (2026)

Disentangling Knowledge Representations for Large Language Model Editing
di: Zhang, Mengqi, et al.
Pubblicazione: (2025)

Knowledge Graph Enhanced Large Language Model Editing
di: Zhang, Mengqi, et al.
Pubblicazione: (2024)

Uncovering Overfitting in Large Language Model Editing
di: Zhang, Mengqi, et al.
Pubblicazione: (2024)

UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
di: Wang, Wenyu, et al.
Pubblicazione: (2025)

Self-Supervised Position Debiasing for Large Language Models
di: Liu, Zhongkun, et al.
Pubblicazione: (2024)

Revealing and Mitigating Over-Attention in Knowledge Editing
di: Wang, Pinzheng, et al.
Pubblicazione: (2025)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
di: Zhang, Mengqi, et al.
Pubblicazione: (2024)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
di: Lyu, Yougang, et al.
Pubblicazione: (2024)

The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
di: Wang, Zheng, et al.
Pubblicazione: (2026)

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
di: Gupta, Akshat, et al.
Pubblicazione: (2024)

Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing
di: Gupta, Akshat, et al.
Pubblicazione: (2025)

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Cross-Lingual Multi-Hop Knowledge Editing
di: Khandelwal, Aditi, et al.
Pubblicazione: (2024)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
di: Wang, Changyue, et al.
Pubblicazione: (2025)

Constraining Sequential Model Editing with Editing Anchor Compression
di: Xu, Hao-Xiang, et al.
Pubblicazione: (2025)

Understanding the Collapse of LLMs in Model Editing
di: Yang, Wanli, et al.
Pubblicazione: (2024)

On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models
di: Cao, Ding, et al.
Pubblicazione: (2025)

Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
di: Lin, Zihao, et al.
Pubblicazione: (2024)

Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
di: Sun, Zengkui, et al.
Pubblicazione: (2024)

Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
di: Fang, Tianqing, et al.
Pubblicazione: (2023)

Identifying and Mitigating Social Bias Knowledge in Language Models
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
di: Duan, Zenghao, et al.
Pubblicazione: (2025)

ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers
di: Hu, Junyan, et al.
Pubblicazione: (2024)

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
di: Zhang, Jiayi, et al.
Pubblicazione: (2025)

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
di: Xu, Derong, et al.
Pubblicazione: (2024)

Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
di: Pei, Jiahuan, et al.
Pubblicazione: (2024)

$μ$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models
di: Su, Zian, et al.
Pubblicazione: (2025)

Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
di: Cao, Han, et al.
Pubblicazione: (2024)

Learning by Surprise: Surplexity for Mitigating Model Collapse in Generative AI
di: Gambetta, Daniele, et al.
Pubblicazione: (2024)

DeepEdit: Knowledge Editing as Decoding with Constraints
di: Wang, Yiwei, et al.
Pubblicazione: (2024)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
di: Hu, Chenhui, et al.
Pubblicazione: (2024)

Knowledge Editing for Large Language Models: A Survey
di: Wang, Song, et al.
Pubblicazione: (2023)

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
di: Zhao, Yukun, et al.
Pubblicazione: (2025)

Event-level Knowledge Editing
di: Peng, Hao, et al.
Pubblicazione: (2024)

Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms
di: Ye, Xiaotian, et al.
Pubblicazione: (2025)

Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection
di: Liu, Ye, et al.
Pubblicazione: (2024)

Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion
di: Gu, Hengrui, et al.
Pubblicazione: (2024)

COMPKE: Complex Question Answering under Knowledge Editing
di: Cheng, Keyuan, et al.
Pubblicazione: (2025)

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
di: Zhang, Zhuoran, et al.
Pubblicazione: (2024)