Latent Coherence: Do Frontier Language Models' Probability Judgments Obey the Law of Total Probability?
arXiv:2610.31833v1 Announce Type: new Abstract: LawZero's Scientist AI trains a Predictor toward the Bayesian posterior, with an objective that penalizes inconsistent probabilities among latent explanations. We ask whether current frontier language models, with no such training, are already consist…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv cs.CL
Latent Coherence: Do Frontier Language Models' Probability Judgments Obey the Law of Total Probability?