Cover Image

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yezi, Chen, Hanning, Huang, Wenjun, Ni, Yang, Imani, Mohsen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples
by: Liu, Yezi, et al.
Published: (2025)

Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing
by: Liu, Yezi, et al.
Published: (2025)

Cauchy-Schwarz Fairness Regularizer
by: Liu, Yezi, et al.
Published: (2025)

Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval
by: Liu, Yezi, et al.
Published: (2025)

LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
by: Huang, Yining, et al.
Published: (2025)

LoRA Learns Less and Forgets Less
by: Biderman, Dan, et al.
Published: (2024)

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
by: Zhou, Hongyun, et al.
Published: (2024)

Promoting Fairness in Link Prediction with Graph Enhancement
by: Liu, Yezi, et al.
Published: (2024)

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture
by: Han, Jiayi, et al.
Published: (2024)

Mixture of LoRA Experts
by: Wu, Xun, et al.
Published: (2024)

AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing
by: Li, Jiacheng, et al.
Published: (2025)

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
by: Gupta, Prakhar, et al.
Published: (2026)

LoRA-GA: Low-Rank Adaptation with Gradient Approximation
by: Wang, Shaowen, et al.
Published: (2024)

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
by: Azimi, Rambod, et al.
Published: (2024)

Aletheia: Gradient-Guided Layer Selection for Efficient LoRA Fine-Tuning Across Architectures
by: Saket, Abdulmalek
Published: (2026)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
by: Yang, Ziyu, et al.
Published: (2026)

A Note on LoRA
by: Fomenko, Vlad, et al.
Published: (2024)

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
by: Lee, Seungeon, et al.
Published: (2025)

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

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
by: Prabhakar, Akshara, et al.
Published: (2024)

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
by: Yen, Jui-Nan, et al.
Published: (2024)

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
by: Shang, Bingqi, et al.
Published: (2025)

Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing
by: Cheng, Ming, et al.
Published: (2025)

DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
by: Zhang, Yuxuan, et al.
Published: (2024)

Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach
by: Huang, Wenjun, et al.
Published: (2024)

Mitigating Bias in Graph Hyperdimensional Computing
by: Liu, Yezi, et al.
Published: (2025)

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
by: Qin, Haotong, et al.
Published: (2024)

PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models
by: Hayou, Soufiane, et al.
Published: (2025)

SEQR: Secure and Efficient QR-based LoRA Routing
by: Fleshman, William, et al.
Published: (2025)

LoRA+: Efficient Low Rank Adaptation of Large Models
by: Hayou, Soufiane, et al.
Published: (2024)

Improving LoRA with Variational Learning
by: Cong, Bai, et al.
Published: (2025)

Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
by: Das, Devleena, et al.
Published: (2025)

Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning
by: Xia, Wenhan, et al.
Published: (2024)

Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks
by: Li, Zongqian, et al.
Published: (2026)

QuAILoRA: Quantization-Aware Initialization for LoRA
by: Lawton, Neal, et al.
Published: (2024)

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
by: Li, Yanan, et al.
Published: (2025)

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance
by: Zhang, Hao, et al.
Published: (2025)

Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
by: Sabry, Mohammed, et al.
Published: (2026)

LoRA vs Full Fine-tuning: An Illusion of Equivalence
by: Shuttleworth, Reece, et al.
Published: (2024)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
by: Lee, Yu-Ang, et al.
Published: (2026)