arXiv:2606. 10669v1 Announce Type: cross Abstract: Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.
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...
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
arXiv:2606. 16535v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols.
arXiv:2606. 07180v1 Announce Type: cross Abstract: The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research.
arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.
arXiv:2606. 11267v1 Announce Type: new Abstract: Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise.
arXiv:2608. 19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data.
arXiv:2503. 07325v2 Announce Type: replace Abstract: Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning.
arXiv:2510. 15770v4 Announce Type: replace-cross Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control.
For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere presence of such secrets in a model's context window introduces hidden correlations into the model's benign outputs, allowing reconstruction even when the model correctly refuses direct extraction.
arXiv:2607. 23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations.
arXiv:2606. 16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications.