arXiv:2607. 02964v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does.
By Arnau Marin-Llobet, Stefan Heimersheim
arXiv:2512. 10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.
By Chaomeng Lu, Bert Lagaisse
arXiv:2509. 23806v2 Announce Type: replace-cross Abstract: Concolic testing for neural networks alternates concrete execution with constraint solving to search for inputs that flip model decisions.
By Chih-Duo Hong, Chih-Cheng Yang, Yu Wang, Fang Yu
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
The paper proposes a new unsupervised safety detection method for large language models that relies on anomaly detection rather than supervised training on unsafe data. By leveraging local sparsity in a linear representation space obtained via a sparse autoencoder, the authors develop a framework for locally masked SAE-based anomaly detection, providing theoretical support and empirical validation across multiple architectures and datasets. When calibrated with only 1% out-of-distribution data, the method achieves near‑optimal performance while using just 1–2% of SAE neurons for computation.
By Xin Chen, Gil Kur, Alexander Shevchenko, Andreas Krause
The paper proposes a novel unsupervised safety detection method for large language models that relies on local sparsity in a linear representation space recovered via a sparse autoencoder. By masking SAE neurons based on shared active support among nearby points, the authors develop a locally masked anomaly detection framework with theoretical backing. Experiments across multiple architectures and datasets—including capability‑testing and safety‑specific sets—show that using only 1–2% of SAE neurons and a small amount of out‑of‑distribution data yields near‑optimal safety detection performance.