arXiv Artificial IntelligenceThe Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice
arXiv:2608.28930v1 Announce Type: cross Abstract: Hidden-state probes effectively detect LLM hallucinations…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.28930v1 Announce Type: cross Abstract: Hidden-state probes effectively detect LLM hallucinations…
arXiv Artificial IntelligencearXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning…
arXiv Artificial IntelligencearXiv:2608.28907v1 Announce Type: cross Abstract: Task handover requires communicating enough current state…
arXiv Artificial IntelligencearXiv:2608.28886v1 Announce Type: cross Abstract: What does a generation loop gain from learning on its own…
arXiv Artificial IntelligencearXiv:2608.28878v1 Announce Type: cross Abstract: This paper develops a hybrid offline-online multi-agent…
arXiv Artificial IntelligencearXiv:2608.28875v1 Announce Type: cross Abstract: Supplying context at inference time to a large multimodal…
arXiv Artificial IntelligencearXiv:2608.28859v1 Announce Type: cross Abstract: Reasoning models do not stop when they know the answer. On…
arXiv Artificial IntelligencearXiv:2608.28853v1 Announce Type: cross Abstract: Equivariant graph neural networks provide a principled way…
arXiv Artificial IntelligencearXiv:2608.28846v1 Announce Type: cross Abstract: Layer-skipping methods for efficient LLM inference decide…
arXiv Artificial IntelligencearXiv:2608.28844v1 Announce Type: cross Abstract: Ensuring a safe virtual reality (VR) experience requires…
arXiv Artificial IntelligencearXiv:2608.28843v1 Announce Type: cross Abstract: We show that smooth two-layer feed-forward networks (FFNs)…
arXiv Artificial IntelligencearXiv:2608.28837v1 Announce Type: cross Abstract: We conducted an interview study with twelve students on…