Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2310.16295v2 Announce Type: replace-cross Abstract: Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is sti...
arXiv:2410.08776v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learnin...
arXiv:2503.11006v3 Announce Type: replace-cross Abstract: Vision and Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions,...
arXiv:2506.12045v2 Announce Type: replace-cross Abstract: Accurate reconstruction of latent environmental fields from sparse, indirect observations is a fundamental challenge across scientific domain...
arXiv:2509.12635v4 Announce Type: replace-cross Abstract: We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention sco...
arXiv:2510.11454v2 Announce Type: replace-cross Abstract: Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solel...
arXiv:2603.00039v2 Announce Type: replace-cross Abstract: LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw:...
arXiv:2604.19984v2 Announce Type: replace-cross Abstract: Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs g...
arXiv:2605.10889v2 Announce Type: replace-cross Abstract: On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions...
arXiv:2605.27750v2 Announce Type: replace-cross Abstract: Recent work has shown that Vision-Language Models (VLMs) used for optical character recognition (OCR) can generate plausible but visually uns...
arXiv:2606.15277v2 Announce Type: replace-cross Abstract: Graph-based recommendation models effectively capture high-order collaborative signals from user--item interaction graphs. Federated learning...
arXiv:2609.05770v1 Announce Type: new Abstract: Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see a...
arXiv:2609.06042v1 Announce Type: new Abstract: This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and i...
arXiv:2609.06093v1 Announce Type: new Abstract: Connectomes, graph-level maps of neurons and their synaptic connections, provide a structural basis for understanding how brain circuits support functi...
arXiv:2609.06173v1 Announce Type: new Abstract: Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradatio...
arXiv:2609.06426v1 Announce Type: new Abstract: Small additive ensembles of symbolic rules offer interpretable prediction models. Traditionally, these ensembles use rule conditions based on conjuncti...
arXiv:2609.06460v1 Announce Type: new Abstract: Recently, Masked Pretraining (MPT) based on reconstruction pretraining tasks has risen to a promising self-supervised learning paradigm across various...
arXiv:2609.06514v1 Announce Type: new Abstract: Adaptive frequency hopping against predictive jamming must address both model uncertainty and policy exposure: the context-loss relationship may vary a...
arXiv:2609.06667v1 Announce Type: new Abstract: Adaptive dosing requires policies that reduce tumor burden without excessive toxicity. Learned dosing policies are typically judged against historical...
arXiv:2609.06976v1 Announce Type: new Abstract: As medical wearables become integrated into daily chronic disease care, effectively interpreting longitudinal monitoring data is essential for patients...