CAP: Controllable Alignment Prompting for Unlearning in LLMs

• URL: http://arxiv.org/abs/2604.21251v2
• Date: Fri, 24 Apr 2026 02:46:01 GMT
• Title: CAP: Controllable Alignment Prompting for Unlearning in LLMs
• Abstract summary: Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information.<n>Existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access.<n>We propose the Controllable Alignment Prompting for Unlearning framework, an end-to-end prompt-driven unlearning paradigm.
• Score: 19.554047742421197
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement [50.91045324738942]
  CLAIM is an uncertainty-driven framework for active clarification learning in open-domain settings.<n>We propose an entropy-driven synthetic data generation pipeline that integrates uncertainty estimation with semantic clustering and reasoning-based judgments.<n> Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data.
  arXiv  Detail & Related papers  (2026-08-12T04:27:45Z)
• MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models [64.2820121997882]
  MIITA is a Memory-Induced Inference-Time Adaptation framework for supervised CL under constrained storage.<n>It stores supervised experiences as compact correction-direction prototypes with semantic anchors, and retrieves them at inference time using semantic and uncertainty-based cues.<n>Experiments show that MIITA consistently improves final performance and mitigates forgetting under fixed memory budgets.
  arXiv  Detail & Related papers  (2026-05-20T03:03:04Z)
• ASACK : Adaptive Safe Active Continual Koopman Learning for Uncertain Systems with Contractive Guarantees [0.38887448816036313]
  Koopman operator theory provides a framework for representing nonlinear dynamics through a linear operator acting on lifted observables.<n>We propose a unified framework for continual adaptive Koopman learning that enables safe and efficient online refinement of learned models.<n>The proposed approach unifies learning, deployment, and safety within a control framework without sacrificing real-time efficiency.
  arXiv  Detail & Related papers  (2026-05-10T17:11:51Z)
• CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment [14.853204323785334]
  Existing approaches, rooted in Gradient Ascent (GA), often degrade general domain knowledge while relying on retention data or curated contrastive pairs.<n>We develop a principled method that rescales unlearning effects in proportion to the model's token-level confidence.<n>Our work enables effective unlearning without requiring retention data or contrastive unlearning response pairs.
  arXiv  Detail & Related papers  (2026-02-02T21:23:54Z)
• Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting [0.0]
  Large language models in sensitive domains can't ensure that private information can be permanently forgotten.<n>Retraining from the beginning is prohibitively costly.<n>Existing unlearning methods remain fragmented, difficult to verify, and often vulnerable to recovery.
  arXiv  Detail & Related papers  (2025-11-13T01:29:05Z)
• MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering [36.80441487363007]
  MLLMEraser is an input-aware, training-free framework for test-time unlearning.<n>We construct a multimodal erasure direction by contrasting adversarially perturbed, knowledge-recall image-text pairs.<n>Experiments on LLaVA-1.5 and Qwen-2.5-VL demonstrate that MLLMEraser consistently outperforms state-of-the-art MLLM unlearning baselines.
  arXiv  Detail & Related papers  (2025-10-05T14:20:17Z)
• Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions [49.55618517046225]
  Language models trained on web-scale corpora risk memorizing and exposing sensitive information.<n>We propose Corrective Unlearning with Retrieved Exclusions (CURE), a novel unlearning framework.<n>CURE verifies model outputs for leakage and revises them into safe responses.
  arXiv  Detail & Related papers  (2025-09-30T09:07:45Z)
• SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs [7.120986296945107]
  This paper investigates an approach called SafeSteer for guiding the outputs of large language models (LLMs)<n>We employ a simple, gradient-free unsupervised method to enhance safety steering while preserving text quality, topic relevance, and without explicit refusal.
  arXiv  Detail & Related papers  (2025-06-01T01:19:37Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [52.40798352740857]
  We introduce the Iterative Contrastive Unlearning (ICU) framework, which consists of three core components.<n>A Knowledge Unlearning Induction module targets specific knowledge for removal using an unlearning loss.<n>A Contrastive Learning Enhancement module preserves the model's expressive capabilities against the pure unlearning goal.<n>An Iterative Unlearning Refinement module dynamically adjusts the unlearning process through ongoing evaluation and updates.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)
• Large Language Model Unlearning via Embedding-Corrupted Prompts [10.889859281637406]
  We present textbfEmbedding-COrrupted (ECO) Prompts, a lightweight unlearning framework for large language models. We enforce an unlearned state during inference by employing a prompt classifier to identify and safeguard prompts to forget. We find that these embedding-corrupted prompts not only lead to desirable outputs that satisfy the unlearning objective but also closely approximate the output from a model that has never been trained on the data intended for forgetting.
  arXiv  Detail & Related papers  (2024-06-12T06:56:20Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.