Buchumschlag

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hu, Chenhui, Cao, Pengfei, Chen, Yubo, Liu, Kang, Zhao, Jun
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Towards Atoms of Large Language Models
von: Hu, Chenhui, et al.
Veröffentlicht: (2025)

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
von: Xie, Jiakuan, et al.
Veröffentlicht: (2025)

EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
von: Cao, Pengfei, et al.
Veröffentlicht: (2025)

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
von: Chen, Yuheng, et al.
Veröffentlicht: (2024)

One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
von: Cao, Pengfei, et al.
Veröffentlicht: (2024)

MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation
von: Xie, Jiakuan, et al.
Veröffentlicht: (2024)

CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph
von: Zhou, Tong, et al.
Veröffentlicht: (2024)

Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
von: Chen, Yuheng, et al.
Veröffentlicht: (2024)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
von: Li, Jiachun, et al.
Veröffentlicht: (2024)

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering
von: Liu, Jiaxiang, et al.
Veröffentlicht: (2024)

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
von: Men, Tianyi, et al.
Veröffentlicht: (2024)

Unveiling the Pitfalls of Knowledge Editing for Large Language Models
von: Li, Zhoubo, et al.
Veröffentlicht: (2023)

The Knowledge Microscope: Features as Better Analytical Lenses than Neurons
von: Chen, Yuheng, et al.
Veröffentlicht: (2025)

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

Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

Neighboring Perturbations of Knowledge Editing on Large Language Models
von: Ma, Jun-Yu, et al.
Veröffentlicht: (2024)

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
von: Chen, Qizhou, et al.
Veröffentlicht: (2024)

CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance
von: Hao, Yupu, et al.
Veröffentlicht: (2024)

Mechanistic Circuit-Based Knowledge Editing in Large Language Models
von: Zhao, Tianyi, et al.
Veröffentlicht: (2026)

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
von: Jin, Zhuoran, et al.
Veröffentlicht: (2024)

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
von: Yuan, Hongbang, et al.
Veröffentlicht: (2024)

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

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
von: Zhou, Chenxi, et al.
Veröffentlicht: (2025)

Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models
von: Liu, Jiaxiang, et al.
Veröffentlicht: (2025)

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

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
von: Li, Jiachun, et al.
Veröffentlicht: (2024)

SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
von: Cao, Pengfei, et al.
Veröffentlicht: (2026)

Identifying Knowledge Editing Types in Large Language Models
von: Li, Xiaopeng, et al.
Veröffentlicht: (2024)

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

Cross-Lingual Knowledge Editing in Large Language Models
von: Wang, Jiaan, et al.
Veröffentlicht: (2023)

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
von: Chen, Qizhou, et al.
Veröffentlicht: (2024)

Stable Knowledge Editing in Large Language Models
von: Wei, Zihao, et al.
Veröffentlicht: (2024)

Reinforced Lifelong Editing for Language Models
von: Li, Zherui, et al.
Veröffentlicht: (2025)

GeoEdit: Geometric Knowledge Editing for Large Language Models
von: Feng, Yujie, et al.
Veröffentlicht: (2025)

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

Commonsense Knowledge Editing Based on Free-Text in LLMs
von: Huang, Xiusheng, et al.
Veröffentlicht: (2024)