{
  "abstract": "Large language models (LLMs) have been proposed to map free-text seizure semiology to seizure-onset-zone (SOZ) likelihoods, but it remains unclear whether inference-time interventions can improve on the original SemioLLM benchmark without additional training. We evaluated two such interventions, candidate-order permutation within self-consistency and TF-IDF retrieval of case-specific labelled examples, individually and in combination (retrieval-augmented order-invariant self-consistency, RAOI-SC), across seven locally served open-weight LLMs on 1,268 Semio2Brain rows. Performance was assessed with weighted- and macro-F1, paired bootstrap confidence intervals, and exact McNemar tests against the self-consistency baseline, and a multi-dimensional reliability profile covering citation coverage and conditional verifiability, retrieval agreement, strict schema adherence, and confidence concentration; a TF-IDF nearest-neighbor classifier and grouped-split sensitivity analyses bounded how much of any gain could reflect retrieval leakage rather than the intervention itself. RAOI-SC had a higher weighted-F1 point estimate than self-consistency for six of seven models, but the improvement was supported by paired confidence intervals for four models and by McNemar testing for only one, Mistral-7B-Instruct-v0.3; the TF-IDF nearest-neighbor baseline alone achieved 55.72 weighted-F1 under row-level splitting, falling to 50.43 and 48.97 once identical-text and publication-reference duplicates were grouped together. These results support a cautious, model-specific reading of retrieval and order permutation as testable prompting interventions rather than a universally superior or clinically validated method, and define a row-level benchmark that does not by itself establish patient- or source-level generalization.",
  "abstract_shown": true,
  "affiliations": [
    "Unit 1, Department of Neurology, Longhua Hospital, Shanghai University of Traditional Chinese Medicine",
    "Shanghai Minhang District Traditional Chinese Medicine Hospital"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Xiaolei Yuan"
    },
    {
      "affs": [
        0
      ],
      "name": "Xinyue Zhang"
    },
    {
      "affs": [
        1
      ],
      "name": "Hui Xu"
    },
    {
      "affs": [
        0
      ],
      "name": "Qing Ye"
    },
    {
      "affs": [
        0
      ],
      "name": "Canxing Yuan"
    },
    {
      "affs": [
        0
      ],
      "name": "Hui Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dcg36wq7cbny8.bib",
  "cited_by": 0,
  "doi": "10.3389/fneur.2026.1990185",
  "fulltext_url": null,
  "id": "dcg36wq7cbny8",
  "issns": [
    "1664-2295"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fneur.2026.1990185/full",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-29",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/dcg36wq7cbny8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:16Z",
      "native_id": "10.3389/fneur.2026.1990185",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fneur.2026.1990185/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:1664-2295",
      "subfield": "neurology"
    }
  ],
  "title": "Toward trustworthy diagnostic AI: debiasing and grounding large language models for seizure semiology interpretation",
  "title_text": "Toward trustworthy diagnostic AI: debiasing and grounding large language models for seizure semiology interpretation",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T00:21:08Z",
  "url": "https://research.draconitic.com/paper/dcg36wq7cbny8",
  "venue": "Frontiers in Neurology",
  "versions": []
}