Image de couverture de livre

Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Xiyu, Si, Qingyi, Liu, Zhengxiao, Yang, Chenxu, Gu, Naibin, Lin, Zheng
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Causal Path Alignment: Anchoring the Optimization Trajectory for Controllable In-Parameter Knowledge Editing
par: Liu, Xiyu, et autres
Publié: (2025)

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
par: Liu, Xiyu, et autres
Publié: (2024)

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
par: Yang, Chenxu, et autres
Publié: (2025)

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
par: Zhao, Jiaxuan, et autres
Publié: (2025)

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
par: Gu, Naibin, et autres
Publié: (2025)

Weights-Rotated Preference Optimization for Large Language Models
par: Yang, Chenxu, et autres
Publié: (2025)

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
par: Gu, Naibin, et autres
Publié: (2024)

System 1&2 Synergy via Dynamic Model Interpolation
par: Yang, Chenxu, et autres
Publié: (2026)

Self-Distilled RLVR
par: Yang, Chenxu, et autres
Publié: (2026)

Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
par: Duan, Zenghao, et autres
Publié: (2025)

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts
par: Feng, Yuchen, et autres
Publié: (2025)

A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
par: Chen, Siyuan, et autres
Publié: (2024)

Are Large Language Models Table-based Fact-Checkers?
par: Zhang, Hanwen, et autres
Publié: (2024)

Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?
par: Wang, Yatong, et autres
Publié: (2026)

Knowledge Editing for Large Language Models: A Survey
par: Wang, Song, et autres
Publié: (2023)

Neighboring Perturbations of Knowledge Editing on Large Language Models
par: Ma, Jun-Yu, et autres
Publié: (2024)

Knowledge Graph Enhanced Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2024)

Disentangling Knowledge Representations for Large Language Model Editing
par: Zhang, Mengqi, et autres
Publié: (2025)

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
par: Ju, Tianjie, et autres
Publié: (2024)

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
par: Hu, Chenhui, et autres
Publié: (2024)

Mechanistic Circuit-Based Knowledge Editing in Large Language Models
par: Zhao, Tianyi, et autres
Publié: (2026)

Advantageous Parameter Expansion Training Makes Better Large Language Models
par: Gu, Naibin, et autres
Publié: (2025)

BeamLoRA: Beam-Constraint Low-Rank Adaptation
par: Gu, Naibin, et autres
Publié: (2025)

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
par: Xu, Derong, et autres
Publié: (2024)

Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models
par: Wang, Chang, et autres
Publié: (2025)

Test-time Prompt Intervention
par: Yang, Chenxu, et autres
Publié: (2025)

Stable Knowledge Editing in Large Language Models
par: Wei, Zihao, et autres
Publié: (2024)

Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference
par: Wang, Lanrui, et autres
Publié: (2023)

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

Dynamic Early Exit in Reasoning Models
par: Yang, Chenxu, et autres
Publié: (2025)

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
par: Hsueh, Cheng-Hsun, et autres
Publié: (2024)

Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models
par: Gu, Leijiang, et autres
Publié: (2026)

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
par: Chen, Ruizhe, et autres
Publié: (2024)

Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
par: Jiang, Minhao, et autres
Publié: (2026)

Benchmarking and Rethinking Knowledge Editing for Large Language Models
par: He, Guoxiu, et autres
Publié: (2025)

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

Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond
par: Li, Qiyuan, et autres
Publié: (2025)

Editing Conceptual Knowledge for Large Language Models
par: Wang, Xiaohan, et autres
Publié: (2024)

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
par: Liu, Tianci, et autres
Publié: (2025)

HATS: High-Accuracy Triple-Set Watermarking for Large Language Models
par: Hu, Zhiqing, et autres
Publié: (2025)