LLM Unlearning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 150% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 129

All topics

Inference-Time Machine Unlearning via Gated Activation Redirection
May 12, 2026Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante +7Activation Steering Machine Unlearning
MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil · Harvard University · Kunumi Institute, Brazil
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
May 12, 2026Zeguan Xiao, Xuanzhe Xu, Yun Chen +4Neural Representation Geometry LLM Security
Shanghai University of Finance and Economics · Southern University of Science and Technology · Alibaba Group +1
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
May 9, 2026Renjie Gu, Jiazhen Du, Yihua Zhang +1LLM Unlearning LLM Honesty
Fudan University · Central South University · Michigan State University
Position: The Term "Machine Unlearning" Is Overused in LLMs
May 8, 2026Sangyeon Yoon, Yeachan Jun, Albert NoLLM Evaluation Machine Unlearning
Department of Artificial Intelligence, Yonsei University, Seoul, Korea.
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
May 8, 2026Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei +3Machine Unlearning LLM Unlearning
University of Southern California · USC Information Sciences Institute
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
May 7, 2026Yuhang Wang, Wenjie Mei, Junkai Zhang +3Privacy-Preserving Language Models Multimodal Large Language Models
School of Computer Science and Technology Xidian University
Retain-Neutral Surrogates for Min-Max Unlearning
May 7, 2026Junhao Cai, Dohun Kim, Dowon Kim +4Machine Unlearning LLM Unlearning
Korea University
DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
May 4, 2026Abdullah Ahmad Khan, Ferdous SohelQuantization-Aware Training 4-Bit Quantization
Murdoch University
Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
May 3, 2026Chenchen Tan, Xinghao Li, Shujie Cui +3Privacy-Preserving Language Models Machine Unlearning
Faculty of Information Technology, Monash University, Clayton, Victoria, Australia. · Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China. · Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, China.
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
May 3, 2026Anamika Paul Rupa, Anietie AndyMemorization in Language Models Neural Network Memorization
Howard University
LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning
May 1, 2026Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar +1LLM Hallucination Mitigation Hallucination in Language Models
University of Texas San Antonio San Antonio, TX, USA · University of California San Diego La Jolla, CA, USA
Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
May 1, 2026Jiawei Wu, Doudou ZhouLLM Unlearning
Department of Statistics and Data Science, National University of Singapore.
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
Apr 23, 2026Xiaoyi Chen, Haoyuan Wang, Siyuan Tang +4LLM Auditing Privacy Leakage in Language Models
Indiana University Bloomington · Independent Researcher · Michigan State University +2
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
Apr 23, 2026Chris Schneider, Philipp Schoenegger, Ben BariachLLM Personalization Privacy-Preserving Language Models
Microsoft AI
CAP: Controllable Alignment Prompting for Unlearning in LLMs
Apr 23, 2026Zhaokun Wang, Jinyu Guo, Jingwen Pu +7LLM Alignment LLM Unlearning
School of Information and Software Engineering, University of Electronic Science and Technology of China
Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
Apr 20, 2026Seunghee Koh, Sunghyun Baek, Youngdong Kim +1Machine Unlearning LLM Unlearning
Korea Advanced Institute of Science and Technology, South Korea · Hanbat National University, South Korea
Representation-Guided Parameter-Efficient LLM Unlearning
Apr 19, 2026Zeguan Xiao, Lang Mo, Yun Chen +4Machine Unlearning LLM Unlearning
Shanghai University of Finance and Economics · Southern University of Science and Technology · Deepexi Technology Co. Ltd.
Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
Apr 17, 2026Ziwen Liu, Huawei Lin, Yide Ran +5Machine Unlearning LLM Unlearning
Rice University · Rochester Institute of Technology · Stevens Institute of Technology +1
CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
Apr 17, 2026Junyi Li, Yongqiang Chen, Ningning DingMachine Unlearning LLM Unlearning
The Hong Kong University of Science and Technology (Guangzhou) · The Chinese University of Hong Kong
Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
Apr 16, 2026Yisheng Zhong, Sijia Liu, Zhuangdi ZhuPrivacy-Preserving Language Models LLM Unlearning
George Mason University · Michigan State University
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
Apr 16, 2026Zeguan Xiao, Siqing Li, Yong Wang +4Gradient Interference Multi-Task Learning
1Shanghai University of Finance and Economics · 2Southern University of Science and Technology · 3Alibaba Group +2
CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
Apr 16, 2026Seyun Bae, Seokhan Lee, Eunho YangPrivacy-Preserving Language Models Factual Knowledge in Language Models
1KT Corporation · 2KAIST
CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
Apr 16, 2026Yian Wang, Yuen Chen, Agam Goyal +1Causal Reasoning in Language Models LLM Safety
Department of Computer Science University of Illinois, Urbana-Champaign Champaign, IL 61801
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
Feb 21, 2026Chahana Dahal, Ashutosh Balasubramaniam, Zuobin XiongMachine Unlearning LLM Unlearning
University of Nevada, Las Vegas · Indian Institute of Technology Guwahati
CALIBURN: Self-Calibrated LLM Unlearning Alignment
Feb 2, 2026Zhengbang Yang, Yisheng Zhong, Junyuan Hong +1LLM Unlearning
George Mason University · National University of Singapore
Contrastive Representation Shaping for LLM Unlearning
Jan 29, 2026Haoran Tang, Rajiv KhannaDisentangled Representation Learning Machine Unlearning
Department of Computer Science, Purdue University.
Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities
Jan 29, 2026Tien Dang, The-Hai Nguyen, Dinh Mai Phuong +5Linear Representation Hypothesis Controllable Text Generation
Japan Advanced Institute of Science and Technology · Monash University · Quantum AI and Cyber Security Institute, FPT Corporation +1
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
Jan 14, 2026Pengyang Shao, Naixin Zhai, Lei Chen +4Distributionally Robust Optimization LLM Unlearning
National University of Singapore Singapore · University of Science and Technology of China Hefei, China · Hefei University of Technology Hefei, China
A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs
Dec 7, 2025Humzah Merchant, Bradford LevyLLM-Based Time Series Forecasting LLM Unlearning
University of Chicago Chicago, IL 60637
RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
Dec 4, 2025Guoshenghui Zhao, Huawei Lin, Weijie ZhaoMachine Unlearning LLM Unlearning
Golisano College of Computing and Information Sciences, Rochester Institute of Technology

May 12, 2026, cs.LGJ/K move · Enter open · S save

Inference-Time Machine Unlearning via Gated Activation Redirection

Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante, Kristen K. Arguello+6

MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil · Harvard University · Kunumi Institute, Brazil

Activation Steering Machine Unlearning LLM Unlearning

Open paper AskPDF arXiv

Large Language Models (LLMs) memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model performance, ideally approximating a model retrained from scratch without it. Once an LLM is in use, every new request to make it forget specific content demands updating its weights. However, unlearning through parameter updates is expensive, hard to audit, and can be undone by quantization. We show that unlearning can be enforced entirely at inference time, without training, gradients, or weight changes. We introduce Inference-Time Unlearning via Gated Activation Redirection (GUARD-IT), a training- and gradient-free method that unlearns via input-dependent activation steering at inference time. GUARD-IT stores the content to be forgotten as a small library of activation directions, and during inference, it routes each query through a similarity gate that activates only for relevant directions and applies them as a norm-preserving rotation of the residual stream, while unrelated queries pass through the unmodified model. The same design carries across three model families and nine checkpoints from 0.8B to 8B parameters, and new forget requests are absorbed by one offline pass of forward passes. On TOFU, against 16 gradient-based and inference-time baselines, and on MUSE and WMDP, GUARD-IT forgets without breaking the model, and on TOFU it is the only method that suppresses memorization in every Llama configuration without collapsing: it keeps utility and fluent generation in every configuration, moves the model's output distribution closest to a model that never saw the forgotten data on the forget01 split, survives 4- and 8-bit quantization and ten sequential forget requests, and holds under jailbreak attacks.

Momentum

Related topics

Latest papers 129