The paper investigates whether representational entanglement—shared structure between knowledge domains—impedes unlearning in neural networks. By training six 254M‑parameter language models with varying degrees of disentanglement between biology and non‑biology knowledge and applying three unlearning methods, the authors find that more disentangled models consistently achieve better retain‑forget trade‑offs, with up to four‑fold lower retain cost. This controlled experiment provides direct evidence that entanglement contributes to collateral damage during unlearning, supporting a long‑standing hypothesis in interpretability research.
The paper investigates how the structural entanglement of facts within a large language model’s knowledge base influences whether those facts leak after unlearning. Using two unlearning algorithms (WHP and GA+KL) across fictional and real-world datasets and multiple model sizes, the authors find that highly entangled facts are more likely to be recalled before unlearning, but the relationship changes—WHP weakens it while GA+KL reverses it. By directly manipulating entanglement scores and observing corresponding recall changes, they demonstrate a causal link and develop a predictive tool to audit prompts for potential leakage.
By Aakriti Shah, Yifan Hu, Thai Le
arXiv:2601.22028v2 Announce Type: replace
Abstract: Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives...
By Haoran Tang, Rajiv Khanna
arXiv:2508.20443v3 Announce Type: replace
Abstract: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership...
By Zhihao Liu, Jian Lou, Yuke Hu, Xiaochen Li, Yitian Chen, Tailun Chen, Zhizhen Qin, Kui Ren, Zhan Qin
arXiv:2502. 15543v4 Announce Type: replace-cross Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence.
By Pengcheng Huang, Zhenghao Liu, Yukun Yan, Haiyan Zhao, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong
arXiv:2507. 07754v3 Announce Type: replace-cross Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores.
By Jaeheun Jung, Bosung Jung, Suhyun Bae, Donghun Lee
arXiv:2606. 13873v1 Announce Type: new Abstract: Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model.
By Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan
arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.
By Zhe Yu, Wenpeng Xing, Tiancheng Zhao, Mohan Li, Changting Lin, Meng Han
arXiv:2607. 08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information.
By Jack Hopkins, Dipika Khullar, Fabien Roger
arXiv:2604. 07650v2 Announce Type: replace Abstract: The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent?
By Chenchen Kuai, Jiwan Jiang, Zihao Zhu, Hao Wang, Keshu Wu, Zihao Li, Yunlong Zhang, Chenxi Liu, Zhengzhong Tu, Zhiwen Fan, Yang Zhou
The paper investigates how machine unlearning for large language models (LLMs) can unintentionally erase related knowledge, even in distant domains. By analyzing the propagation of unlearning effects before any model updates, the authors discover a consistent decay pattern where collateral damage is strongest near the targeted forget set and diminishes with semantic distance but never fully disappears at domain boundaries. They propose a pre-unlearning prediction task—forget-set auditing—to identify potential collateral damage early, finding that interaction features between the forget set and evaluation set are the most predictive signals. This approach offers an early warning system for risky unlearning runs and guides the design of more reliable unlearning procedures.
By Bo Su, Ankit Shah, Thai Le
arXiv:2609.36612v1 Announce Type: new
Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...
By Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong