Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 08014v1 Announce Type: cross Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications.
arXiv:2606. 07521v1 Announce Type: cross Abstract: This study investigates the phenomenon of hallucinations in domain-adapted Large Language Models (LLMs), focusing on the fine-tuning of the Llama-2 model with the Lamini dataset.
arXiv:2606. 08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment.
arXiv:2606. 08179v1 Announce Type: cross Abstract: Subgraph counting is a fundamental problem in graph analysis.
arXiv:2606. 08158v1 Announce Type: cross Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.
arXiv:2604. 07125v2 Announce Type: replace-cross Abstract: This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation.
arXiv:2605. 01616v2 Announce Type: replace-cross Abstract: Human behavior is challenging to measure continuously at scale, yet traces of daily routines and well-being may be reflected in interactions with personal devices.
arXiv:2605. 06582v2 Announce Type: replace Abstract: Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures.
arXiv:2604. 07848v2 Announce Type: replace Abstract: Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principled framework for predicting these outcomes.
arXiv:2412. 16457v3 Announce Type: replace-cross Abstract: In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence.
arXiv:2602. 15829v2 Announce Type: replace Abstract: The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge.
arXiv:2601. 23221v2 Announce Type: replace Abstract: As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical resort.
arXiv:2506. 23033v2 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment.
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
arXiv:2511. 03877v2 Announce Type: replace Abstract: Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years later, by higher impact like citations, sales, or reviews.
arXiv:2511. 05355v3 Announce Type: replace Abstract: Flow matching (FM) has shown promising results in data-driven planning.
arXiv:2606. 07660v1 Announce Type: cross Abstract: Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.
arXiv:2606. 07647v1 Announce Type: cross Abstract: Large vision language models (LVLMs) have made rapid advancements and are deployed across various applications, yet hallucinations remain a major challenge.
arXiv:2602. 01357v2 Announce Type: replace Abstract: Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data.
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.