# CAP: Controllable Alignment Prompting for Unlearning in LLMs

arXiv: https://arxiv.org/abs/2604.21251 · HTML: https://mlsanity.com/paper/2604.21251/

## 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 28 of its 48 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Guardrail Baselines for Unlearning in LLMs](https://mlsanity.com/paper/2403.03329/) (2024)
- [Guiding Large Language Models via Directional Stimulus Prompting](https://mlsanity.com/paper/2302.11520/) (2023)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [STAIR: Improving Safety Alignment with Introspective Reasoning](https://mlsanity.com/paper/2502.02384/) (2025)
- [Iteratively Prompt Pre-trained Language Models for Chain of Thought](https://mlsanity.com/paper/2203.08383/) (2022)
- [Soft Prompting for Unlearning in Large Language Models](https://mlsanity.com/paper/2406.12038/) (2024)
- [PRewrite: Prompt Rewriting with Reinforcement Learning](https://mlsanity.com/paper/2401.08189/) (2024)
- [Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective](https://mlsanity.com/paper/2407.16997/) (2024)
- [Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation](https://mlsanity.com/paper/2308.08090/) (2023)
- [Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.11537/) (2024)
- [Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models](https://mlsanity.com/paper/2603.13394/) (2026)
- [ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting](https://mlsanity.com/paper/2403.14312/) (2024)
- [DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning](https://mlsanity.com/paper/2511.05784/) (2025)
- [HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation](https://mlsanity.com/paper/2505.16133/) (2025)
- [Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE](https://mlsanity.com/paper/2505.23868/) (2025)
- [ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs](https://mlsanity.com/paper/2603.01792/) (2026)

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

- [Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness](https://mlsanity.com/paper/2608.04519/) (2026)
- [Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality](https://mlsanity.com/paper/2608.23020/) (2026)
- [Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning](https://mlsanity.com/paper/2609.16890/) (2026)

## Abstract (arXiv)

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access. These constraints render them impractical for closed-source models, yet current non-invasive alternatives remain unsystematic and reliant on empirical experience. To address these challenges, we propose the Controllable Alignment Prompting for Unlearning (CAP) framework, an end-to-end prompt-driven unlearning paradigm. CAP decouples unlearning into a learnable prompt optimization process via reinforcement learning, where a prompt generator collaborates with the LLM to suppress target knowledge while preserving general capabilities selectively. This approach enables reversible knowledge restoration through prompt revocation. Extensive experiments demonstrate that CAP achieves precise, controllable unlearning without updating model parameters, establishing a dynamic alignment mechanism that overcomes the transferability limitations of prior methods.