Cover Image

LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Anjarlekar, Ameya, Pombra, Sandeep
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Scalable Policy-Based RL Algorithms for POMDPs
by: Anjarlekar, Ameya, et al.
Published: (2025)

Striking a Balance: An Optimal Mechanism Design for Heterogenous Differentially Private Data Acquisition for Logistic Regression
by: Anjarlekar, Ameya, et al.
Published: (2023)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
by: Huang, Tao, et al.
Published: (2024)

Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning
by: Dolgova, Polina, et al.
Published: (2026)

Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator
by: Han, Haoyu, et al.
Published: (2026)

Delta-Influence: Unlearning Poisons via Influence Functions
by: Li, Wenjie, et al.
Published: (2024)

Targeted Unlearning with Single Layer Unlearning Gradient
by: Cai, Zikui, et al.
Published: (2024)

Label Smoothing Improves Gradient Ascent in LLM Unlearning
by: Pang, Zirui, et al.
Published: (2025)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
by: Wang, Qizhou, et al.
Published: (2025)

Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio
by: Wen, Ziqing, et al.
Published: (2026)

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
by: Chen, Sirui, et al.
Published: (2026)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
by: Chien, Eli, et al.
Published: (2024)

Corrective Machine Unlearning
by: Goel, Shashwat, et al.
Published: (2024)

Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
by: Liu, Yezi, et al.
Published: (2025)

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
by: Huang, Zhehao, et al.
Published: (2024)

Unlearning Backdoor Attacks through Gradient-Based Model Pruning
by: Dunnett, Kealan, et al.
Published: (2024)

Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
by: Kim, Yejin, et al.
Published: (2025)

CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
by: Miao, Jiaxing, et al.
Published: (2025)

Descend or Rewind? Stochastic Gradient Descent Unlearning
by: Mu, Siqiao, et al.
Published: (2025)

Less Noise, Same Certificate: Retain Sensitivity for Unlearning
by: Heinzler, Carolin, et al.
Published: (2026)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
by: Spohn, Philipp, et al.
Published: (2025)

Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients
by: Van Waerebeke, Martin, et al.
Published: (2026)

LLM Unlearning with LLM Beliefs
by: Li, Kemou, et al.
Published: (2025)

Improving Unlearning with Model Updates Probably Aligned with Gradients
by: Dine, Virgile, et al.
Published: (2025)

Spectrum: Targeted Training on Signal to Noise Ratio
by: Hartford, Eric, et al.
Published: (2024)

One-Step Score-Based Density Ratio Estimation
by: Chen, Wei, et al.
Published: (2026)

Gauss-Newton Unlearning for the LLM Era
by: McKinney, Lev, et al.
Published: (2026)

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
by: Hu, Zizhao, et al.
Published: (2026)

Upcycling Noise for Federated Unlearning
by: Chen, Jianan, et al.
Published: (2024)

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
by: Ju, Bocheng, et al.
Published: (2025)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
by: Huang, Zhuo, et al.
Published: (2026)

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
by: Doshi, Jai, et al.
Published: (2024)

Controllable Machine Unlearning via Gradient Pivoting
by: Hwang, Youngsik, et al.
Published: (2025)

SIMU: Selective Influence Machine Unlearning
by: Agarwal, Anu, et al.
Published: (2025)

Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
by: Sun, Yuhao, et al.
Published: (2025)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

Diffusion Secant Alignment for Score-Based Density Ratio Estimation
by: Chen, Wei, et al.
Published: (2025)

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
by: Patel, Gaurav, et al.
Published: (2025)

Staying on the Manifold: Geometry-Aware Noise Injection
by: Jacobsen, Albert Kjøller, et al.
Published: (2025)

Search-contempt: a hybrid MCTS algorithm for training AlphaZero-like engines with better computational efficiency
by: Joshi, Ameya
Published: (2025)