Image de couverture de livre

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Wanli, Sun, Fei, Ma, Xinyu, Liu, Xun, Yin, Dawei, Cheng, Xueqi
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Understanding the Collapse of LLMs in Model Editing
par: Yang, Wanli, et autres
Publié: (2024)

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
par: Bi, Baolong, et autres
Publié: (2024)

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
par: Tan, Hexiang, et autres
Publié: (2024)

The Mirage of Model Editing: Revisiting Evaluation in the Wild
par: Yang, Wanli, et autres
Publié: (2025)

Should We Really Edit Language Models? On the Evaluation of Edited Language Models
par: Li, Qi, et autres
Publié: (2024)

Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions
par: Cassano, Federico, et autres
Publié: (2023)

Can We Edit Multimodal Large Language Models?
par: Cheng, Siyuan, et autres
Publié: (2023)

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
par: Wu, Jiaxuan, et autres
Publié: (2025)

Are We Evaluating the Edit Locality of LLM Model Editing Properly?
par: Liu, Wei, et autres
Publié: (2026)

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
par: Fang, Junfeng, et autres
Publié: (2024)

K-Edit: Language Model Editing with Contextual Knowledge Awareness
par: Markowitz, Elan, et autres
Publié: (2025)

InstructEdit: Instruction-based Knowledge Editing for Large Language Models
par: Zhang, Ningyu, et autres
Publié: (2024)

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
par: Wang, Peng, et autres
Publié: (2023)

Investigating Context Effects in Similarity Judgements in Large Language Models
par: Uprety, Sagar, et autres
Publié: (2024)

BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models
par: Deng, Fei, et autres
Publié: (2026)

Has this Fact been Edited? Detecting Knowledge Edits in Language Models
par: Youssef, Paul, et autres
Publié: (2024)

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
par: Cheng, Yinjie, et autres
Publié: (2025)

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
par: Cheng, Xueqi, et autres
Publié: (2026)

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents
par: Li, Yongxiang, et autres
Publié: (2026)

DLLMQuant: Quantizing Diffusion-based Large Language Models
par: Xu, Chen, et autres
Publié: (2025)

BiasEdit: Debiasing Stereotyped Language Models via Model Editing
par: Xu, Xin, et autres
Publié: (2025)

Large Language Models Can Self-Improve in Long-context Reasoning
par: Li, Siheng, et autres
Publié: (2024)

Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models
par: Liu, Dingning, et autres
Publié: (2024)

ExpressEdit: Video Editing with Natural Language and Sketching
par: Tilekbay, Bekzat, et autres
Publié: (2024)

ReasonEdit: Editing Vision-Language Models using Human Reasoning
par: Qiu, Jiaxing, et autres
Publié: (2026)

DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models
par: Shi, Zhiyi, et autres
Publié: (2025)

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
par: Zhang, Hengran, et autres
Publié: (2025)

Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models
par: Huang, Liangjie, et autres
Publié: (2025)

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
par: Cheng, Xueqi, et autres
Publié: (2026)

Can Large Language Models Act as Ensembler for Multi-GNNs?
par: Duan, Hanqi, et autres
Publié: (2024)

Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing
par: Baghel, Bhiman Kumar, et autres
Publié: (2025)

Identifying Knowledge Editing Types in Large Language Models
par: Li, Xiaopeng, et autres
Publié: (2024)

GraphGPT: Graph Instruction Tuning for Large Language Models
par: Tang, Jiabin, et autres
Publié: (2023)

Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
par: Ma, Xueqi, et autres
Publié: (2025)

Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
par: Zeng, Zhen, et autres
Publié: (2024)

Large Language Model Sourcing: A Survey
par: Pang, Liang, et autres
Publié: (2025)

A Survey of Large Language Models for Graphs
par: Ren, Xubin, et autres
Publié: (2024)

Can Large Language Models do Analytical Reasoning?
par: Hu, Yebowen, et autres
Publié: (2024)

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

Internal Safety Collapse in Frontier Large Language Models
par: Wu, Yutao, et autres
Publié: (2026)