{
  "abstract": "Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation is slow and unscalable. We ask whether coefficient priors elicited from large language models (LLMs) improve out-of-distribution (OOD) prediction as the shrinkage target of a regularised regression instead of zero, across five tabular datasets split on real covariates, selecting providers and prior structures by source-domain cross-validation alone. The priors help on four of five datasets, by up to 7.9% OOD mean squared error, and ten of twenty-four prior-informed results resolve the mean improvement at conventional confidence; single-deployment intervals are much wider. On classification the gain is in probabilistic accuracy, not ranking, and control tests with corrupted priors attribute the benefit to feature-specific content rather than scale. Two findings temper this. Variation across candidate priors exceeds the average benefit, yet cross-validation margins fall below their own noise, so selection avoids the worst prior rather than finding the best. On three datasets the prior improves in-domain accuracy as much as out-of-domain, making it better regularisation than shift correction. Only where the training data are large enough that the in-domain gain disappears does elicited knowledge demonstrably improve transfer. Code, priors and results: https://github.com/hugohammer/llm-priors-ood.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.36806",
  "author_total": 3,
  "authors": [
    {
      "name": "Sølve Langseth"
    },
    {
      "name": "Kristoffer Herland Hellton"
    },
    {
      "name": "Hugo L. Hammer"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8r4b1jcg55zpk.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.36806",
  "fulltext_url": null,
  "id": "8r4b1jcg55zpk",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.36806",
  "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.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Domain Adaptation and Few-Shot Learning"
    ]
  ],
  "openalex": "W7224078985",
  "pdf_url": "https://arxiv.org/pdf/2610.36806",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8r4b1jcg55zpk.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:59Z",
      "native_id": "2610.36806",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.36806"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach",
  "title_text": "LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:59Z",
  "url": "https://research.draconitic.com/paper/8r4b1jcg55zpk",
  "venue": "arXiv",
  "versions": []
}