Tag
This paper studies whether training logs from stochastic runs can improve the precision of model comparisons via arm-specific covariate adjustment, finding that simple adjustments can reduce uncertainty, though careful covariate selection is needed to avoid noise.
This paper demonstrates that training large language models with stochastic tokenization instead of deterministic canonical tokenization significantly improves robustness to adversarial attacks and random perturbations, with improvements shown across pre-training, fine-tuning, and in-context learning without increasing inference costs.