Image de couverture de livre

Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luong, Hoang-Chau, Chen, Lingwei
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

Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
par: Xu, Runze, et autres
Publié: (2026)

LoRA+: Efficient Low Rank Adaptation of Large Models
par: Hayou, Soufiane, et autres
Publié: (2024)

LoRA-GA: Low-Rank Adaptation with Gradient Approximation
par: Wang, Shaowen, et autres
Publié: (2024)

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
par: Meng, Xiangdi, et autres
Publié: (2024)

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
par: Yang, Yaming, et autres
Publié: (2024)

HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation
par: Chen, Lixian, et autres
Publié: (2026)

ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition
par: Ma, Xindian, et autres
Publié: (2026)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
par: Deng, Guanzhi, et autres
Publié: (2026)

BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
par: Chang, Yupeng, et autres
Publié: (2024)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
par: Ran, Delong, et autres
Publié: (2025)

LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
par: Bałazy, Klaudia, et autres
Publié: (2024)

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
par: Wang, Hanqing, et autres
Publié: (2024)

LoRA Learns Less and Forgets Less
par: Biderman, Dan, et autres
Publié: (2024)

LoRA$^2$ : Multi-Scale Low-Rank Approximations for Fine-Tuning Large Language Models
par: Zhang, Jia-Chen, et autres
Publié: (2024)

Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
par: Das, Devleena, et autres
Publié: (2025)

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
par: Vaidya, Omatharv Bharat, et autres
Publié: (2026)

$D^2LoRA$: Data-Driven LoRA Initialization for Low Resource Tasks
par: SeraJ, Javad, et autres
Publié: (2025)

LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimization
par: Chang, Yupeng, et autres
Publié: (2025)

AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing
par: Li, Jiacheng, et autres
Publié: (2025)

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
par: Gupta, Prakhar, et autres
Publié: (2026)

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
par: Wang, Zhengbo, et autres
Publié: (2024)

LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning
par: Zhang, Longteng, et autres
Publié: (2023)

DenseLoRA: Dense Low-Rank Adaptation of Large Language Models
par: Mu, Lin, et autres
Publié: (2025)

LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
par: Xiao, Yicheng, et autres
Publié: (2025)

ChunkWise LoRA: Adaptive Sequence Partitioning for Memory-Efficient Low-Rank Adaptation and Accelerated LLM Inference
par: Thakkar, Ketan, et autres
Publié: (2026)

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
par: Liu, Yezi, et autres
Publié: (2025)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
par: Xu, Yixing, et autres
Publié: (2025)

MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning
par: Zhang, Jingfan, et autres
Publié: (2024)

RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization
par: Liu, Dongqi, et autres
Publié: (2024)

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

Weight space Detection of Backdoors in LoRA Adapters
par: Merenciano, David Puertolas, et autres
Publié: (2026)

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
par: Liu, Hongyi, et autres
Publié: (2024)

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
par: Li, Yanan, et autres
Publié: (2025)

LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference
par: Rajabzadeh, Hossein, et autres
Publié: (2026)

L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
par: Singh, Raul, et autres
Publié: (2025)

OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning
par: Xiong, Yifeng, et autres
Publié: (2025)

QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning
par: Rajabzadeh, Hossein, et autres
Publié: (2024)

Null-LoRA: Low-Rank Adaptation on Null Space
par: Zhang, Yi, et autres
Publié: (2025)

Vision as LoRA
par: Wang, Han, et autres
Publié: (2025)

FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
par: Sathyavageeswaran, Ramakrishnan
Publié: (2026)