Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 15127v1 Announce Type: new Abstract: Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input.
arXiv:2606. 16763v1 Announce Type: cross Abstract: When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP guarantee for the joint output.
arXiv:2606. 16219v1 Announce Type: cross Abstract: Digital twin modeling, including control and data assimilation under model uncertainty, often faces an open-ended fidelity problem: adding variables, data streams, and time scales can indefinitely increase model complexity, ultimately producing systems that are difficult to maintain, validate, interpret, and use for stress or safety testing.
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
arXiv:2606. 15756v1 Announce Type: cross Abstract: Lane-change prediction is a central task in intelligent vehicles, where early maneuver anticipation can support safer decision-making.
arXiv:2606. 15331v1 Announce Type: cross Abstract: Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective.
arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.
arXiv:2505. 23593v4 Announce Type: replace Abstract: Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks.
arXiv:2606. 16914v1 Announce Type: new Abstract: Deployed agents increasingly act with their reward proxy in view, such as a balance, score, or KPI dashboard.
arXiv:2606. 16368v1 Announce Type: cross Abstract: Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols, both of which lack interpretability.
arXiv:2512. 16184v2 Announce Type: replace Abstract: Early and accessible detection of Alzheimer's disease (AD) remains a critical clinical challenge, and cube-copying tasks offer a simple yet informative assessment of visuospatial function.
arXiv:2606. 16753v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use.
arXiv:2601. 18699v2 Announce Type: replace Abstract: Sequential fine-tuning of Large Language Models (LLMs) adaptation to target tasks often triggers catastrophic forgetting, where the acquisition of novel target skills degrades ancestral capabilities.
arXiv:2606. 14718v1 Announce Type: cross Abstract: As Artificial Intelligence (AI) literacy initiatives expand in K-12 settings, understanding how gender shapes student baseline perceptions, tool-use, and responsiveness to interventions is essential for equitable curriculum design.
arXiv:2606. 16923v1 Announce Type: new Abstract: Simulation-based inference (SBI) of latent parameters is often hindered by simulator misspecification, the mismatch between simulated and real-world observations caused by inherent modeling simplifications.
arXiv:2606. 11692v1 Announce Type: cross Abstract: Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2501. 01908v4 Announce Type: replace-cross Abstract: Deep learning (DL) methods have become the state-of-the-art for reconstructing sub-sampled magnetic resonance imaging (MRI) data.
arXiv:2605. 18909v2 Announce Type: replace Abstract: Any system that models the world under finite representational capacity must compress; any compression entails a prior; and the prior is the system's bias.
arXiv:2605. 01961v2 Announce Type: replace Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents.