{
  "abstract": "An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that function to the answer received. The difficulty is that observed losses reflect both expert quality and an unfinished correction: early errors can discourage queries that would be valuable after learning. We propose ORUCB, which pools shared and expert-specific polynomial responses. A bound on cumulative response-learning error calibrates confidence-weighted risk regression and exploration, allowing the router to account for this error when deciding which answers to buy. Under bounded residuals and disagreements, a fixed feasible model of optimal responses, and linear models of free and optimal queried risk, the calibrated algorithm achieves high-probability pseudo-regret $O(\\sqrt T\\log(T+1))$ over $T$ rounds for fixed problem parameters. The guarantee permits singular answer distributions and misspecified shared responses; optimality is relative to the bounded response class. On four test streams, the selected cubic policy has lower fee-inclusive cost than seven baselines that deploy answers unchanged. Comparisons with a common correction learner examine routing, while six-price comparisons measure cost and query rates.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.07084",
  "author_total": 4,
  "authors": [
    {
      "name": "Yannis Montreuil"
    },
    {
      "name": "Axel Carlier"
    },
    {
      "name": "Lai Xing Ng"
    },
    {
      "name": "Wei Tsang Ooi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7vnxatsr533k4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.07084",
  "fulltext_url": null,
  "id": "7vnxatsr533k4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.07084",
  "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.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1803|Advanced Bandit Algorithms Research"
    ]
  ],
  "openalex": "W7221038917",
  "pdf_url": "https://arxiv.org/pdf/2610.07084",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7vnxatsr533k4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:32Z",
      "native_id": "2610.07084",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.07084"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral",
  "title_text": "A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:32Z",
  "url": "https://research.draconitic.com/paper/7vnxatsr533k4",
  "venue": "arXiv",
  "versions": []
}