Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases.
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.
arXiv:2608. 12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions.
arXiv:2608. 12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success.
arXiv:2608. 13136v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention.
arXiv:2608. 12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey.
arXiv:2608. 13495v1 Announce Type: cross Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis.
arXiv:2608. 13209v1 Announce Type: cross Abstract: Many operational decisions are sequences of interventions under a cumulative resource limit, such as a maintenance schedule within a crew-hour budget.
arXiv:2603. 19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications.
arXiv:2512. 02694v3 Announce Type: replace-cross Abstract: We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding.
arXiv:2608. 13133v1 Announce Type: cross Abstract: Distributional shifts arise when the target deployment environment differs from the source environment that generated the training data.
arXiv:2608. 12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by malicious actors for censorship and manipulation.
arXiv:2608. 12360v1 Announce Type: cross Abstract: Background: AI/ML-enabled medical devices are increasingly deployed in healthcare under evolving regulatory frameworks.
arXiv:2608. 13190v1 Announce Type: new Abstract: Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable.
arXiv:2608. 12791v1 Announce Type: cross Abstract: What a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity.
arXiv:2608. 13513v1 Announce Type: cross Abstract: Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers.
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv:2608. 12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries.
arXiv:2608. 13467v1 Announce Type: new Abstract: We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ \pi(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is convex and \(G\)-Lipschitz.
arXiv:2608. 12535v1 Announce Type: new Abstract: Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring.