An Empirical Audit of k-NAF Budget Accounting for Anchored Decoding
Not on the map. Why?
Abstract (arXiv)
We empirically audit the k-NAF budget-accounting mechanism in Anchored Decoding using (i) a fixed, class-stratified workload (approximately 8,500 randomized executions across six prompt classes) and (ii) an adaptive prompt-search procedure targeting high proxy spend ratios. On the fixed workload, mean cumulative KL spend remains far below the sequence-level budgets K in {600, 1000}, and an empirical Bernstein-style proxy stays below K for every class; surface-overlap diagnostics (ROUGE-L and 5-gram Jaccard) are correspondingly small. Adaptive search increases the proxy spend ratio but does not produce clear budget exhaustion. On a held-out copyright-domain workload at k = 3, several prompts exhibit proxy ratios above 1 under early-stopped evaluations with small realized sample sizes; re-evaluating the same prompts with larger allocation reduces the proxy ratio to the range [0.26, 0.40] under comparable mean spend, consistent with proxy artifacts rather than per-trajectory budget failures.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 10 references that are in the map. First posted on arXiv 27 May 2026.
Builds on
6 of 10 references.
References · 6
- 2022Red Teaming Language Models with Language Modelscited by 983
- 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
- 2015Illuminating search spaces by mapping elitescited by 406
- 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
- 2023Privacy Auditing with One (1) Training Runcited by 119
- 2023On Provable Copyright Protection for Generative Modelscited by 97
Built on by
Not cited yet.