{
  "abstract": "BackgroundLarge language models (LLMs) may answer cancer questions plausibly while accepting a false presupposition (FP). Prompts that increase FP correction may also challenge questions in which no FP is present (NFP). We compared SkillOpt, an automated skill-optimisation method developed by Microsoft Research, with conventional prompt engineering across models.\n\nMethodsUsing the physician-verified Cancer-Myth benchmark, GPT-5.4 optimised a written skill for GPT-4o in three independent 12-step executions. Training used 117 FP questions. Rewrites were selected by combined accuracy on a validation set of 58 FP and 30 NFP questions, then tested on 410 unseen FP questions. A separate GPT-4o judged responses. Across seven LLMs, we compared no correction instruction, a deliberately strong seven-example few-shot prompt, three GPT-5.4-generated instruction-only prompts, and full and compact SkillOpt skills. Further tests examined portability, new questions and valid clinical assumptions.\n\nResultsSkillOpt increased GPT-4o FP correction from 15.4-17.6% to 82.2-90.5%, gains of 66.3-72.9 percentage points (95% bootstrap confidence intervals 61.7-77.3; all Holm-adjusted p<0.001). Only two or three rewrites were accepted per execution. The first full skill achieved 92.7-96.6% correction on three recipient models but 6.3-16.3% on two weaker models, where few-shot prompting achieved 44.6-54.6%. On Gemini 3.5 Flash and GPT-5.6 Luna, compact SkillOpt retained 90.0-92.9% correction while increasing NFP accuracy from 59.2-79.2% with the full skill to 85.8-93.3%. Both approaches sometimes challenged valid clinical assumptions.\n\nConclusionsSkillOpt produced large, repeatable gains, but it was neither universally portable nor free of over-correction. Automated and conventional prompts should be compared for each intended model using tests of both FP correction and NFP accuracy. Compact SkillOpt may improve this balance on capable models.",
  "abstract_shown": true,
  "affiliations": [
    "Royal Marsden Hospital/Institute of Cancer Research"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. Khanna"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/86r11mdd430wd.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.08.26362559",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362559v1.full",
  "id": "86r11mdd430wd",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362559v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "oncology"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7212242088",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362559v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/86r11mdd430wd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:16Z",
      "native_id": "10.64898/2026.09.08.26362559",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362559v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:oncology",
      "subfield": "oncology"
    }
  ],
  "title": "Automated Skill Optimisation for False Presupposition Handling in Cancer Communication: SkillOpt Versus Conventional Prompt Engineering Across Language Models",
  "title_text": "Automated Skill Optimisation for False Presupposition Handling in Cancer Communication: SkillOpt Versus Conventional Prompt Engineering Across Language Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:16Z",
  "url": "https://research.draconitic.com/paper/86r11mdd430wd",
  "venue": "medRxiv",
  "versions": []
}