arXiv:2609.37076v1 Announce Type: new
Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...
By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen
The paper introduces GONE, a benchmark for evaluating knowledge unlearning in large language models using structured knowledge graphs, and presents Neighborhood-Expanded Distribution Shaping (NEDS), a framework that leverages graph connectivity to separate forgotten facts from their semantic neighborhood. GONE disentangles direct fact removal, reasoning-based leakage, and catastrophic forgetting, while NEDS achieves high unlearning efficacy and locality on LLaMA-3-8B and Mistral-7B. The dataset is publicly available on Hugging Face.
By Chahana Dahal, Ashutosh Balasubramaniam, Zuobin Xiong
The paper introduces the problem of cross‑lingual loopholes in large language model (LLM) unlearning, where forgetting a fact in one language can leave it accessible in others. It presents a new 174‑language benchmark, the Cross‑Lingual Unlearning Tensor, and proposes COVER, a method that selects a subset of source languages to maximize unlearning coverage under a language budget. Experiments show COVER reduces residual knowledge by 7.8–27.3% compared to uniform selection and works on both synthetic and real low‑resource news data.
By Tyler Skow, Shravan Chaudhari, Rama Chellappa, Abhay Yadav
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
By Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei, Mohammad Rostami, Jesse Thomason, Robin Jia
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%.
"whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
By Ivo Brink, Alexander Boer, Dennis Ulmer
arXiv:2605.24614v2 Announce Type: replace-cross
Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether...
By Jaeung Lee, Dohyun Kim, Jaemin Jo