# GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

arXiv: https://arxiv.org/abs/2505.13312 · HTML: https://mlsanity.com/paper/2505.13312/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 87 of its 105 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 87)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)

## Built on by (most cited first, 17 of 17)

- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models](https://mlsanity.com/paper/2510.22535/) (2025)
- [Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning](https://mlsanity.com/paper/2510.00761/) (2025)
- [LM-mixup: Text Data Augmentation via Language Model based Mixup](https://mlsanity.com/paper/2510.20449/) (2025)
- [Label Smoothing Improves Gradient Ascent in LLM Unlearning](https://mlsanity.com/paper/2510.22376/) (2025)
- [Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2606.00105/) (2026)
- [Position: The Term "Machine Unlearning" Is Overused in LLMs](https://mlsanity.com/paper/2606.27379/) (2026)
- [Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning](https://mlsanity.com/paper/2510.00125/) (2025)
- [Divergence Decoding: Inference-Time Unlearning via Auxiliary Models](https://mlsanity.com/paper/2605.31293/) (2026)
- [Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks](https://mlsanity.com/paper/2602.05252/) (2026)
- [CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge](https://mlsanity.com/paper/2604.14644/) (2026)
- [NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding](https://mlsanity.com/paper/2605.10065/) (2026)
- [DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models](https://mlsanity.com/paper/2605.21539/) (2026)
- [Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning](https://mlsanity.com/paper/2606.15333/) (2026)
- [SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning](https://mlsanity.com/paper/2608.02058/) (2026)
- [AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces](https://mlsanity.com/paper/2609.34854/) (2026)
- [Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning](https://mlsanity.com/paper/2610.10655/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains. However, the ability to selectively forget specific knowledge is critical for ensuring the safety and compliance of deployed models. Existing unlearning efforts typically fine-tune the model with resources such as forget data, retain data, and a calibration model. These additional gradient steps blur the decision boundary between forget and retain knowledge, making unlearning often at the expense of overall performance. To avoid the negative impact of fine-tuning, it would be better to unlearn solely at inference time by safely guarding the model against generating responses related to the forget target, without destroying the fluency of text generation. In this work, we propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation. Specifically, we first employ a prompt classifier to detect unlearning targets and extract the corresponding forbidden token. We then dynamically penalize and filter candidate tokens during generation using a combination of token matching and semantic matching, effectively preventing the model from leaking the forgotten content. Experimental results on copyright content unlearning tasks over the Harry Potter dataset and the MUSE benchmark, as well as entity unlearning tasks on the TOFU dataset, demonstrate that GUARD achieves strong forget quality across various tasks while causing almost no degradation to the LLM's general capabilities, striking an excellent trade-off between forgetting and utility.