Reinforcement Unlearning via Group Relative Policy Optimization

• URL: http://arxiv.org/abs/2601.20568v1
• Date: Wed, 28 Jan 2026 13:07:58 GMT
• Title: Reinforcement Unlearning via Group Relative Policy Optimization
• Authors: Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci,
• Abstract summary: We introduce PURGE (Policy Unlearning through Relative Group Erasure), a novel method that formulates unlearning as a verifiable problem.<n>Our approach reduces token usage per target by up to a factor of 46 compared with SotA methods, while improving fluency by 5.48 percent.<n>On the Real World Knowledge Unlearning (RWKU) benchmark, PURGE achieves 11 percent unlearning effectiveness while preserving 98 percent of original utility.
• Score: 20.66330243194323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove information from a deployed model without retraining from scratch. Existing unlearning approaches attempt to address this need, but often leak the very data they aim to erase, sacrifice fluency and robustness, or depend on costly external reward models. We introduce PURGE (Policy Unlearning through Relative Group Erasure), a novel method grounded in the Group Relative Policy Optimization framework that formulates unlearning as a verifiable problem. PURGE uses an intrinsic reward signal that penalizes any mention of forbidden concepts, allowing safe and consistent unlearning. Our approach reduces token usage per target by up to a factor of 46 compared with SotA methods, while improving fluency by 5.48 percent and adversarial robustness by 12.02 percent over the base model. On the Real World Knowledge Unlearning (RWKU) benchmark, PURGE achieves 11 percent unlearning effectiveness while preserving 98 percent of original utility. PURGE shows that framing LLM unlearning as a verifiable task, enables more reliable, efficient, and scalable forgetting, suggesting a promising new direction for unlearning research that combines theoretical guarantees, improved safety, and practical deployment efficiency.

Related papers

• Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization [72.20212909644017]
  Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
  arXiv  Detail & Related papers  (2025-11-20T17:58:04Z)
• GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models [17.83305806604326]
  GUARD is a framework for guided unlearning and retention via data attribution.<n>It assigns adaptive, nonuniform unlearning weights to samples, inversely proportional to their proxy attribution scores.<n>We provide rigorous theoretical guarantees that GUARD significantly improves retention while maintaining forgetting metrics comparable to prior methods.
  arXiv  Detail & Related papers  (2025-06-12T17:49:09Z)
• RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality [24.299312059430704]
  Unlearning is the task of selectively removing specific information from a model without retraining from scratch or degrading overall utility.<n>Existing methods often rely on large-scale forget and retain datasets, and suffer from unnatural responses, poor generalization, or catastrophic utility loss.<n>We propose Reinforcement UnLearning (RULE), an efficient framework that formulates unlearning as a refusal boundary optimization problem.
  arXiv  Detail & Related papers  (2025-06-08T14:38:39Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Privacy-Preserved Automated Scoring using Federated Learning for Educational Research [1.2556373621040728]
  We propose a federated learning (FL) framework for automated scoring of educational assessments.<n>We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline.<n>Results show that our model achieves the highest accuracy (94.5%) among FL approaches.
  arXiv  Detail & Related papers  (2025-03-12T19:06:25Z)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs [25.91643745340183]
  Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora.<n>This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods.<n>We propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs.
  arXiv  Detail & Related papers  (2024-08-13T04:18:32Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
  Humans possess the ability to draw on past experiences explicitly when learning new tasks. We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information. Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
  arXiv  Detail & Related papers  (2023-11-16T09:07:34Z)
• RelaxLoss: Defending Membership Inference Attacks without Losing Utility [68.48117818874155]
  We propose a novel training framework based on a relaxed loss with a more achievable learning target. RelaxLoss is applicable to any classification model with added benefits of easy implementation and negligible overhead. Our approach consistently outperforms state-of-the-art defense mechanisms in terms of resilience against MIAs.
  arXiv  Detail & Related papers  (2022-07-12T19:34:47Z)
• A Regularized Implicit Policy for Offline Reinforcement Learning [54.7427227775581]
  offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. We propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. Experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.
  arXiv  Detail & Related papers  (2022-02-19T20:22:04Z)

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.