Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 13723v1 Announce Type: cross Abstract: Intersection-over-Union (IoU), as a pivotal metric for evaluating the spatial alignment between candidate proposals and ground-truth annotations, directly determines the quality of positive sample sets and the training efficacy of visual detection models.
arXiv:2606. 13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target.
arXiv:2510. 02695v3 Announce Type: replace-cross Abstract: In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) is attractive only if policies achieve high returns without catastrophic lower-tail risk.
arXiv:2605. 09420v2 Announce Type: replace-cross Abstract: In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer.
arXiv:2512. 04981v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) systems increasingly rely on Large Language Model (LLM)-based text conditioning to interpret and expand user prompts.
arXiv:2606. 14268v1 Announce Type: cross Abstract: We develop a statistical learning theory for gradient boosting applied to the estimation of covariate-dependent Generalized Pareto (GP) distributions in the context of Peaks-over-Threshold modeling.
arXiv:2606. 14518v1 Announce Type: new Abstract: The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU.
arXiv:2606. 14117v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evaluated for bias using adaptations of human psychological paradigms, yet methodological limitations-particularly the conflation of refusal behavior with task performance-have hindered clear interpretation.
arXiv:2606. 14149v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved.
arXiv:2604. 18419v5 Announce Type: replace Abstract: LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses.
arXiv:2605. 11558v2 Announce Type: replace Abstract: Activation functions play a central role in neural networks by shaping internal representations.
arXiv:2606. 14608v1 Announce Type: cross Abstract: Survival prediction plays a central role for healthcare providers and clinical researchers.
arXiv:2606. 14536v1 Announce Type: new Abstract: Safe reinforcement learning (RL) aims to learn policies that optimize rewards while satisfying constraints.
arXiv:2508. 18166v5 Announce Type: replace-cross Abstract: Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization.
arXiv:2606. 14594v1 Announce Type: cross Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision.
arXiv:2602. 23638v3 Announce Type: replace-cross Abstract: Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data.
arXiv:2606. 14040v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are typically trained to reconstruct the \textbf{entire} residual stream through a sparse dictionary, implicitly assuming that all activation content is amenable to sparse, monosemantic decomposition.
arXiv:2606. 14060v1 Announce Type: new Abstract: Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors.
arXiv:2606. 13859v1 Announce Type: cross Abstract: Many materials and chemical systems exhibit history-dependent responses, where functional outcomes are governed not only by final-state variables but by the time-dependent sequence of fields, temperatures, or chemical potentials applied during operation.
arXiv:2605. 05983v2 Announce Type: replace Abstract: Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones.