paper-with-me

홈 › Papers

CLUE: Conflict-guided Localization for LLM Unlearning Framework

2025-09-25 · Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang arxiv

The LLM unlearning aims to eliminate the influence of undesirable data without affecting causally unrelated information. This process typically involves using a forget set to remove target information, alongside a retain set to maintain non-target capabilities. While recent localization-based methods demonstrate promise in identifying important neurons to be unlearned, they fail to disentangle neurons responsible for forgetting undesirable knowledge or retaining essential skills, often treating them as a single entangled group. As a result, these methods apply uniform interventions, risking catastrophic over-forgetting or incomplete erasure of the target knowledge. To address this, we turn to circuit discovery, a mechanistic interpretability technique, and propose the Conflict-guided Localization for LLM Unlearning framEwork (CLUE). This framework identifies the forget and retain circuit composed of important neurons, and then the circuits are transformed into conjunctive normal forms (CNF). The assignment of each neuron in the CNF satisfiability solution reveals whether it should be forgotten or retained. We then provide targeted fine-tuning strategies for different categories of neurons. Extensive experiments demonstrate that, compared to existing localization methods, CLUE achieves superior forget efficacy and retain utility through precise neural localization.

📄 PDF Abstract BibTeX arXiv:2509.20977

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating

2025-01-31 · Binchi Zhang, Zhengzhang Chen, Zaiyi Zheng, Jundong Li 외

Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge, but their utility relies on timely updates as knowledge evolves. Updating LLMs involves two key tasks simultaneousl…

Language ModelingLanguage ModellingLarge Language Model

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning

2025-03-08 · Gaurav Patel, Qiang Qiu

Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge…

Machine Unlearning

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

2025-02-03 · Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan 외

Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged to alleviate this concern; however, exist…

Language ModelingLanguage ModellingLarge Language ModelMachine Unlearning

FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented Optimization

2026-02-02 · Zeyan Wang, Zhengmao Liu, Yongxin Cai, Chi Li 외 arxiv

Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a federated model while preserving utility for the remaining clients. However, three key challenges remain: (1) existing unl…

Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks

2026-01-31 · Tian Zhang, Yujia Tong, Junhao Dong, Ke Xu 외 arxiv

The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However, existing methods face critical challen…