# Reveal and Release: Iterative LLM Unlearning with Self-generated Data

arXiv: https://arxiv.org/abs/2509.14624 · HTML: https://mlsanity.com/paper/2509.14624/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Model collapse from synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Model collapse from synthetic data](https://mlsanity.com/synth/model-collapse-from-synthetic-data/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Orthogonal Subspace Learning for Language Model Continual Learning](https://mlsanity.com/paper/2310.14152/) (2023)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Machine Unlearning via Algorithmic Stability](https://mlsanity.com/paper/2102.13179/) (2021)
- [Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation](https://mlsanity.com/paper/2308.08090/) (2023)
- [Unified Parameter-Efficient Unlearning for LLMs](https://mlsanity.com/paper/2412.00383/) (2024)
- [Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models](https://mlsanity.com/paper/2404.00506/) (2024)
- [Delta-Influence: Unlearning Poisons via Influence Functions](https://mlsanity.com/paper/2411.13731/) (2024)
- [Effective Skill Unlearning through Intervention and Abstention](https://mlsanity.com/paper/2503.21730/) (2025)
- [Large Language Models can be Strong Self-Detoxifiers](https://mlsanity.com/paper/2410.03818/) (2024)
- [Adversarial Mixup Unlearning](https://mlsanity.com/paper/2502.10288/) (2025)
- [CMD: a framework for Context-aware Model self-Detoxification](https://mlsanity.com/paper/2308.08295/) (2023)

## Built on by (most cited first, 2 of 2)

- [CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence](https://mlsanity.com/paper/2606.27683/) (2026)
- [Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning](https://mlsanity.com/paper/2608.20960/) (2026)

## Abstract (arXiv)

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or legally regulated, making it expensive or impractical to obtain (2) The distribution of available forget data may not align with how that information is represented within the model. To address these limitations, we propose a ``Reveal-and-Release'' method to unlearn with self-generated data, where we prompt the model to reveal what it knows using optimized instructions. To fully utilize the self-generated forget data, we propose an iterative unlearning framework, where we make incremental adjustments to the model's weight space with parameter-efficient modules trained on the forget data. Experimental results demonstrate that our method balances the tradeoff between forget quality and utility preservation.