AINeutralarXiv – CS AI · 3h ago5/10
🧠
An Empirical Audit of k-NAF Budget Accounting for Anchored Decoding
Researchers empirically tested the k-NAF budget accounting mechanism in Anchored Decoding across 8,500 executions and found that cumulative KL divergence spending remained consistently below sequence-level budgets, with no clear evidence of budget exhaustion even under adaptive stress testing. Results suggest the budget mechanism functions reliably, though some proxy artifacts appeared in small-sample evaluations on copyright-domain workloads.