# GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs

arXiv: https://arxiv.org/abs/2504.12681 · HTML: https://mlsanity.com/paper/2504.12681/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2407.01920/) (2024)
- [Avoiding Copyright Infringement via Large Language Model Unlearning](https://mlsanity.com/paper/2406.10952/) (2024)
- [Machine Unlearning in Large Language Models](https://mlsanity.com/paper/2404.16841/) (2024)

## Built on by (most cited first, 3 of 3)

- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks](https://mlsanity.com/paper/2602.05252/) (2026)
- [Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning](https://mlsanity.com/paper/2609.37858/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) trained on extensive datasets often learn sensitive information, which raises significant social and legal concerns under principles such as the "Right to be forgotten." Retraining entire models from scratch to remove undesired information is both costly and impractical. Furthermore, existing single-domain unlearning methods fail to address multi-domain scenarios, where knowledge is interwoven across domains such as privacy and copyright, creating overlapping representations that lead to excessive knowledge removal or degraded performance. To tackle these issues, we propose GRAIL (GRadient-based AdaptIve unLearning), a novel multi-domain unlearning framework. GRAIL leverages gradient information from multiple domains to precisely distinguish the unlearning scope from the retention scope, and applies an adaptive parameter-wise localization strategy to selectively remove targeted knowledge while preserving critical parameters for each domain. Experimental results on unlearning benchmarks show that GRAIL achieves unlearning success on par with the existing approaches, while also demonstrating up to 17% stronger knowledge retention success compared to the previous state-of-art method. Our findings establish a new paradigm for effectively managing and regulating sensitive information in large-scale pre-trained language models.