arXiv:2507. 02169v2 Announce Type: replace Abstract: Machine learning models are often used in applications where their inputs change due to routine interactions, strategic manipulation, or noise.
arXiv:2505. 08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety.
arXiv:2607. 20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services.
arXiv:2502. 05163v2 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) necessitates effective mechanisms to ensure their responsible deployment by accurately distinguishing unsafe content from benign content.
arXiv:2604. 23099v2 Announce Type: replace-cross Abstract: Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models and benchmarks.
arXiv:2406. 05670v3 Announce Type: replace Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks.
arXiv:2606. 11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model.
arXiv:2506. 20573v4 Announce Type: replace-cross Abstract: Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance.
arXiv:2605. 13801v2 Announce Type: replace-cross Abstract: As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount.
arXiv:2505. 04608v5 Announce Type: replace-cross Abstract: Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continual, post-deployment monitoring to quickly detect and address any unsafe behavior.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.
arXiv:2606. 30136v1 Announce Type: new Abstract: Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm).