{
  "abstract": "Evaluating a stochastic large language model is costly: benchmark scores estimate expected performance from randomized rollouts, yet uniform repetition ignores sharp differences in task-level rollout variance. We ask how to minimize the variance of a fixed-benchmark mean under an exact rollout budget. We develop Speculative Evaluation with a Hierarchical Bayesian Neyman (HBN) policy with pilot size and stage weight jointly chosen ex ante. It runs a short uniform pilot, pools per-task success counts with a hierarchical Bayesian model, and uses posterior expectations of task-level sampling variances for exact positive-integer Neyman allocation. To mitigate the pilot synchronization barrier, HBN-async speculatively executes continuations from partial pilot feedback and retains those selected by the final allocation. Across six checkpoints and 18 benchmark groups, we evaluate 107 nondegenerate benchmark-checkpoint profiles. For rollout budgets of 8-64 per task, Speculative Evaluation reduces variance relative to Uniform by 12.8%-33.6% on average across profiles, outperforming hindsight-tuned empirical and independent Bayesian baselines. Real-generation experiments that account for the pilot synchronization barrier show that HBN-async mitigates its overhead, helping translate statistical efficiency into practical evaluation benefits.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.28560",
  "author_total": 6,
  "authors": [
    {
      "name": "Qianli Shen"
    },
    {
      "name": "Xiang Li"
    },
    {
      "name": "Ruomeng Ding"
    },
    {
      "name": "Yanxi Chen"
    },
    {
      "name": "Daoyuan Chen"
    },
    {
      "name": "Yaliang Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0fq7tf4d71h7k.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.28560",
  "fulltext_url": null,
  "id": "0fq7tf4d71h7k",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.28560",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7214284206",
  "pdf_url": "https://arxiv.org/pdf/2609.28560",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0fq7tf4d71h7k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:21Z",
      "native_id": "2609.28560",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.28560"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Speculative Evaluation of Stochastic LLMs",
  "title_text": "Speculative Evaluation of Stochastic LLMs",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:21Z",
  "url": "https://research.draconitic.com/paper/0fq7tf4d71h7k",
  "venue": "arXiv",
  "versions": []
}