# Pre-Forgettable Models: Prompt Learning as a Native Mechanism for Unlearning

arXiv: https://arxiv.org/abs/2509.15230 · HTML: https://mlsanity.com/paper/2509.15230/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Towards Adversarial Evaluations for Inexact Machine Unlearning](https://mlsanity.com/paper/2201.06640/) (2022)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [LMEraser: Large Model Unlearning through Adaptive Prompt Tuning](https://mlsanity.com/paper/2404.11056/) (2024)

## Built on by (most cited first, 1 of 1)

- [TrustErase: Auditable Instant Machine Unlearning with Passport-Embedded Representations](https://mlsanity.com/paper/2606.17122/) (2026)

## Abstract (arXiv)

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands -- particularly the need to unlearn specific data upon request, as mandated by privacy frameworks such as the GDPR. Traditional unlearning approaches, including retraining, activation editing, or distillation, are often computationally expensive, fragile, and ill-suited for real-time or continuously evolving systems. In this paper, we propose a paradigm shift: rethinking unlearning not as a retroactive intervention but as a built-in capability. We introduce a prompt-based learning framework that unifies knowledge acquisition and removal within a single training phase. Rather than encoding information in model weights, our approach binds class-level semantics to dedicated prompt tokens. This design enables instant unlearning simply by removing the corresponding prompt -- without retraining, model modification, or access to original data. Experiments demonstrate that our framework preserves predictive performance on retained classes while effectively erasing forgotten ones. Beyond utility, our method exhibits strong privacy and security guarantees: it is resistant to membership inference attacks, and prompt removal prevents any residual knowledge extraction, even under adversarial conditions. This ensures compliance with data protection principles and safeguards against unauthorized access to forgotten information, making the framework suitable for deployment in sensitive and regulated environments. Overall, by embedding removability into the architecture itself, this work establishes a new foundation for designing modular, scalable and ethically responsive AI models.