Confabulation at Scale: Information-Theoretic Limits of LLM Faithfulness in Clinical Documentation
Raubenheimer, 2026
Preprint
Read Paper
Frontier AI Auditing: A Comprehensive Framework
Brundage et al., 2026
arXiv:2601.11699
Read Paper
Everything is Context: LLM-as-OS Paradigm
Xu et al., 2025
arXiv:2512.05470
Read Paper
Detecting Hallucinations Using Uncertainty Estimation
Farquhar et al., 2024
Nature 630, 625-630
Read Paper
LLM Susceptibility to Misinformation in Clinical Notes
Omar et al., 2026
Lancet Digital Health
Read Paper