The paper explores ways to reduce the memorization of training data in language models, testing three regularizer-based, three finetuning-based, and eleven machine unlearning methods—five of which are newly introduced. It introduces TinyMem, a lightweight suite of small models for rapid testing of these mitigation techniques, and shows that unlearning methods, particularly BalancedSubnet, outperform others in removing memorized content while maintaining task performance. The study also finds that regularizer-based approaches are slow and ineffective, while finetuning methods are costly, especially when high accuracy is required.
By Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian Foster, Michael W. Mahoney
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u
Output Vector Editing (OVE) is a post‑hoc technique that suppresses unwanted text continuations from large language models by editing the output vectors of specific neurons. It uses a two‑stage localization of MLP layers and neurons combined with full‑vocabulary least‑squares updates, and its multi‑anchor variant (OVE‑MA) adaptively selects continuation positions to maximize suppression. Experiments on models ranging from 360 M to 7 B parameters show that OVE‑MA can reduce recoverable continuations by 24.45 % with only five output‑vector updates, outperforming the prior method REVS while requiring far fewer updates.
By Ahmad Dawar Hakimi, Kaiwei Lei, Isabelle Augenstein, Hinrich Sch\"utze
The paper introduces ADU, a fine‑grained training framework that unlearns sensitive information from large language models by decoupling contextual attention pathways instead of erasing tokens. ADU exploits the distinction between local and global attention heads to identify and suppress attention paths that retrieve persistent sensitive anchors, while preserving local‑attention structure and overall language modeling performance. Evaluation on the TOFU and WMDP benchmarks shows ADU achieves superior forget quality (0.93 on TOFU) and retains 92.9% of model utility compared to 81.9% for existing baselines, with fewer side effects in benign contexts.
By Xunlei Chen, Qirui Ye, Yuang Li, Yi Gong, Zhaokun Wang, Wenyi Li, Shiyao Guo, Jinyu Guo
The paper introduces a Fisher-guided submodular data selection method for continual pre‑training of large language models, addressing the forgetting problem that arises when a target‑domain corpus overwrites pretrained knowledge. By decomposing candidate gradients into anchor and frontier components and optimizing a log‑determinant submodular objective, the method selects data that both improves target‑domain performance and limits forgetting. Experiments on TinyLlama‑1.1B and Llama‑3.1‑8B show that the selector achieves superior adaptation and forgetting control while using ten times fewer tokens than traditional replay strategies.
By Zhenghao Zhao, Gaowen Liu, Zhiling Lan, Yan Yan
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
By Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke Poech
arXiv:2606.12234v2 Announce Type: replace
Abstract: Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the invol...
By Iuri Macocco, Pau Rodr\'iguez, Arno Blaas, Luca Zappella, Marco Baroni, Xavier Suau
arXiv:2606. 31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.
By Francesco Capano, Jonas B\"ohler
The paper introduces Subspace Tuning (SST), a fine‑tuning technique that restricts weight updates to the bottom singular subspace of model parameters, thereby protecting the principal directions that are most prone to catastrophic forgetting. SST is optimizer‑agnostic, works with existing fine‑tuning recipes such as SFT and self‑distillation, and includes dense gradient estimation and a refresh mechanism to enhance learning. Experiments show that SST can preserve up to 99 % of the weight subspace, significantly reduce KL drift, and nearly eliminate forgetting in large‑scale language models while maintaining strong target‑task performance.
By Arnav Chavan, Kusha Sareen, Rishabh Tiwari, Abhranil Chandra, Johan Obando-Ceron, Kurt Keutzer, Scott Niekum, Inderjit S Dhillon, Devvrit Khatri
arXiv:2606. 15092v1 Announce Type: new Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs).
By Minh-Hieu Pham, Bach Do, Laziz Abdullaev, Tan Minh Nguyen, Khoat Than
The paper introduces Subspace Tuning (SST), a fine‑tuning technique that confines weight updates to the bottom singular subspace of model parameters, thereby avoiding changes along principal directions that cause catastrophic forgetting. SST is optimizer‑agnostic, works with existing fine‑tuning recipes, and includes dense gradient estimation and a refresh mechanism. Experiments show that protecting up to 99% of the weight subspace significantly reduces forgetting, improves retention, and maintains strong target‑task performance, especially in large‑model regimes, while also reducing KL drift by 2–4× compared to baseline methods.
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.
By Trishita Tiwari, Ari Trachtenberg, G. Edward Suh