Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Aware Unlearning with Proxy Constraint

• URL: http://arxiv.org/abs/2508.20443v1
• Date: Thu, 28 Aug 2025 05:45:40 GMT
• Title: Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Aware Unlearning with Proxy Constraint
• Authors: Zhihao Liu, Jian Lou, Yuke Hu, Xiaochen Li, Tailun Chen, Yitian Chen, Zhan Qin,
• Abstract summary: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content.<n>Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained models.<n>Most existing methods lack a sound forgetting boundary, causing some samples to be under-forgotten.
• Score: 28.25159814956888
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained models. Machine unlearning provides a practical solution by removing the influence of specific data without full retraining. However, most existing methods lack a sound forgetting boundary, causing some samples to be under-forgotten, leaving residual leakage risks, while others remain over-forgotten at the expense of degraded utility. In this work, we propose EAGLE-PC (Entanglement-Awareness Guided Loss Reweighting with Proxy Constraint), a novel unlearning framework that addresses these limitations through two key components. First, entanglement-awareness guided loss reweighting determines the forgetting effort of each sample by measuring its similarity to retain samples in the embedding space, enabling more targeted and effective unlearning. Second, a proxy constraint leveraging ICL (In-Context Learning) generated test data softly regularizes the forgetting process, effectively mitigating over-forgetting. EAGLE-PC is compatible with existing gradient-based objectives and serves as a plug-and-play enhancement. We evaluate EAGLE-PC on the TOFU and MUSE benchmarks, showing consistent improvements in the forgetting-utility trade-off across multiple LLMs. Combined with the NPO+GD optimizer, it approaches full retraining performance, offering a scalable and robust unlearning solution.

Related papers

• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• Forgetting-MarI: LLM Unlearning via Marginal Information Regularization [6.979586479353831]
  Existing unlearning methods often degrade model performance by removing more information than necessary when attempting to ''forget'' specific data.<n>We introduce Forgetting-MarI, an LLM unlearning framework that provably removes only the additional (marginal) information contributed by the data to be unlearned.<n>By penalizing marginal information, our method yields an explicit upper bound on the unlearn dataset's residual influence in the trained models, providing provable undetectability.
  arXiv  Detail & Related papers  (2025-11-14T22:48:39Z)
• GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models [23.667160042806064]
  GUARD is a novel framework for guided unlearning and retention via data attribution.<n>At its core, GUARD introduces a lightweight proxy data attribution metric tailored for LLM unlearning.<n>We provide rigorous theoretical guarantees that GUARD significantly enhances retention while maintaining forgetting metrics comparable to prior methods.
  arXiv  Detail & Related papers  (2025-06-12T17:49:09Z)
• Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness [30.596695293390415]
  Interpolated Approximate Measurement (IAM) is a framework designed for unlearning inference.<n>IAM quantifies sample-level unlearning completeness by interpolating the model's generalization-fitting behavior gap on queried samples.<n>We apply IAM to recent approximate unlearning algorithms, revealing general risks of both over-unlearning and under-unlearning.
  arXiv  Detail & Related papers  (2025-06-06T14:22:18Z)
• ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining [53.893792844055106]
  Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency.<n>We introduce Selective Efficient Language Modeling, a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection.<n> Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines.
  arXiv  Detail & Related papers  (2025-05-26T12:23:26Z)
• Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution [66.11004226578771]
  Existing robust benchmark datasets have two key limitations.<n>They generate only a limited range of perturbations for a single Information Extraction (IE) task.<n>Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench.<n>We show that training with only textbf15% of the data leads to an average textbf7.5% relative performance improvement across three IE tasks.
  arXiv  Detail & Related papers  (2025-03-05T05:39:29Z)
• LLM Unlearning via Loss Adjustment with Only Forget Data [20.310423152885217]
  We introduce Forget data only Loss AjustmenT (FLAT), a "flat" loss adjustment approach which addresses these issues. Empirical results demonstrate that our approach achieves superior unlearning performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-10-14T23:43:33Z)
• 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)
• On Large Language Model Continual Unlearning [35.49718871265512]
  Machine unlearning has emerged as a representative approach for model safety and security.<n>These methods do not sufficiently consider that unlearning requests in real-world scenarios are continuously emerging.<n>We propose an Orthogonal low-rank adapter (LoRA) for continually unlearning requested data and an Out-Of-Distribution detector to measure the similarity between input and unlearning data.
  arXiv  Detail & Related papers  (2024-07-14T14:26:17Z)
• Offset Unlearning for Large Language Models [49.851093293780615]
  delta-Unlearning is an offset unlearning framework for black-box LLMs.<n>We show that delta-Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks.
  arXiv  Detail & Related papers  (2024-04-17T03:39:51Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Vertical Semi-Federated Learning for Efficient Online Advertising [50.18284051956359]
  Semi-VFL (Vertical Semi-Federated Learning) is proposed to achieve a practical industry application fashion for VFL. We build an inference-efficient single-party student model applicable to the whole sample space. New representation distillation methods are designed to extract cross-party feature correlations for both the overlapped and non-overlapped data.
  arXiv  Detail & Related papers  (2022-09-30T17:59:27Z)

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.