{
  "abstract": "LLM-as-a-judge evaluation commonly aggregates multiple judges' decisions into a majority vote, yet this panel decision process does not guarantee that the evaluation of an individual item is reliable. We propose Structured Cross-fitted Uncertainty Risk (SCUR), a label-free approach for estimating instance-level evaluation reliability based on the judge panel's behavior. A latent measurement model serves as the backbone for measurement system analysis, from which SCUR derives three complementary signals capturing panel uncertainty, measurement cross-entropy, and perturbation sensitivity. These three sources of evidence are combined into a risk score. We evaluate the SCUR approach on five real-world benchmarks using majority-vote error ranking, selective trust, and risk stratification. Furthermore, we show our approach to be more effective at detecting high-consensus risk items, which are the blind spots for many other LLM-as-a-judge evaluation methods.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.14029",
  "author_total": 3,
  "authors": [
    {
      "name": "Yang Ba"
    },
    {
      "name": "Michelle V. Mancenido"
    },
    {
      "name": "Rong Pan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8y06trza7w375.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.14029",
  "fulltext_url": null,
  "id": "8y06trza7w375",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.14029",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Data Classification"
    ]
  ],
  "openalex": "W7221779082",
  "pdf_url": "https://arxiv.org/pdf/2610.14029",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8y06trza7w375.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:26Z",
      "native_id": "2610.14029",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.14029"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge",
  "title_text": "Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/8y06trza7w375",
  "venue": "arXiv",
  "versions": []
}