Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 08417v1 Announce Type: cross Abstract: Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling.
arXiv:2509. 20714v2 Announce Type: replace-cross Abstract: In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well.
arXiv:2606. 07929v1 Announce Type: new Abstract: Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes.
arXiv:2606. 08691v1 Announce Type: new Abstract: Modern data-driven applications increasingly involve learning from multiple heterogeneous sources, where a target dataset is limited but related information is available across domains.
arXiv:2603. 10823v2 Announce Type: replace-cross Abstract: Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution.
arXiv:2606. 09408v1 Announce Type: cross Abstract: We present an ethnographic study of an alternative approach to data work, developed by a civic-tech initiative that builds datasets for training and benchmarking online safety systems.
arXiv:2606. 07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models.
arXiv:2606. 09109v1 Announce Type: cross Abstract: Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins and hard braking.
arXiv:2606. 08067v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.
arXiv:2506. 20699v2 Announce Type: replace Abstract: Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization.
arXiv:2606. 08272v1 Announce Type: cross Abstract: AgriGov is a curated, trilingual (English-Hindi-Marathi) dataset designed to address the scarcity of domain-grounded multilingual resources for agricultural policies and farmer welfare schemes.
arXiv:2603. 29824v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning methods such as LoRA enable efficient adaptation of large pretrained models, but often lag behind full fine-tuning in both convergence speed and final performance.
arXiv:2606. 07629v1 Announce Type: cross Abstract: Current approaches to aligning large language models (LLMs) aggregate diverse human preferences into a single reward signal, effectively optimizing for a hypothetical ``average user'' who represents no real person particularly well.
arXiv:2606. 08238v1 Announce Type: new Abstract: Constitutive modeling of the relationship between process-imposed material states and fundamental material properties is critical to control of material microstructure in manufacturing processes.
arXiv:2605. 19662v2 Announce Type: replace Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed for \emph{non-strategic} settings where data distributions are independent of deployed classifiers.
arXiv:2606. 08236v1 Announce Type: cross Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations that produce them.
arXiv:2606. 08969v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce unsupported claims.
arXiv:2606. 09027v1 Announce Type: cross Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature.
arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.
arXiv:2606. 07908v1 Announce Type: new Abstract: Derivative-controlled networks based on ChainzRule (CR) combine cubic polynomial layers with a lightweight forward-mode per-layer Jacobian penalty (DREG).