{
  "abstract": "Editors of published Korean Easy-Read documents changed 50 aligned sentences by widely varying amounts (edit distance 0.39–0.89), motivating rewrite intensity as a control variable for large language models (LLMs). We ask whether a requested intensity is realized per sentence and whether the level to request can be predicted from the source, using a generation-and-selection pipeline over a frozen LLM (EXAONE-3.5-7.8B-Instruct) in two sequential protocols with criteria hash-frozen before generation. Realized intensity is normalized character edit distance, which measures change, not readability, meaning preservation or Easy-Read quality. A four-level protocol (v1) ordered outputs on average but failed the sentence-level criterion (14/50 under its zero-tolerance rule). A three-level follow-up (v2), designed after that failure with several simultaneous changes, met its criterion for the whole pipeline, including its intensity-aware selector: 41/50 sources were non-decreasingly ordered at the declared tolerance (24/50 with strict increases; post hoc, 30/50 without the selector’s intensity-match term at that tolerance). Three runs of one LLM proxy perceived the ordering (consistency, not validity); no human evaluated the outputs. Stronger levels reduced source similarity without monotonically reducing lexical difficulty. Six source features did not support prediction of the LLM-proxy-preferred level under a pre-specified rule (quadratic-weighted κ −0.098 vs. 0.012), so no adaptive allocation was built. Rewrite-intensity control and level allocation therefore require separate validation.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Artificial Intelligence Convergence, Graduate School, Pukyong National University, Busan 48513, Republic of Korea",
    "Department of Computer Engineering and Artificial Intelligence, Pukyong National University, Busan 48513, Republic of Korea"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jeong-Eun Lee"
    },
    {
      "affs": [
        1
      ],
      "name": "Sang Ho Oh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/20p85bvrgqf0f.bib",
  "cited_by": 0,
  "doi": "10.3390/app162010253",
  "fulltext_url": "https://www.mdpi.com/2076-3417/16/20/10253",
  "id": "20p85bvrgqf0f",
  "issns": [
    "2076-3417"
  ],
  "landing_url": "https://doi.org/10.3390/app162010253",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "QC1-999"
    ],
    [
      "lcc",
      "QD1-999"
    ],
    [
      "lcc",
      "QH301-705.5"
    ],
    [
      "lcc",
      "T"
    ],
    [
      "lcc",
      "TA1-2040"
    ],
    [
      "openalex",
      "1702|Text Readability and Simplification"
    ]
  ],
  "openalex": "W7222451681",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/20p85bvrgqf0f.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T14:21:21Z",
      "native_id": "03d0cf276ca645c1bf9490b21b9160fd",
      "source": "doaj",
      "url": "https://doi.org/10.3390/app162010253"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "lcc:QH301-705.5",
      "subfield": "general"
    },
    {
      "field": "chemistry",
      "origin": "lcc:QD1-999",
      "subfield": "general"
    },
    {
      "field": "physics",
      "origin": "lcc:QC1-999",
      "subfield": "general"
    }
  ],
  "title": "Beyond Binary Rewrite Decisions: Separating Rewrite-Intensity Control from Level Prediction in a Frozen-LLM Generation-and-Selection Pipeline for Korean Easy-Read Drafting",
  "title_text": "Beyond Binary Rewrite Decisions: Separating Rewrite-Intensity Control from Level Prediction in a Frozen-LLM Generation-and-Selection Pipeline for Korean Easy-Read Drafting",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T14:21:21Z",
  "url": "https://research.draconitic.com/paper/20p85bvrgqf0f",
  "venue": "Applied Sciences",
  "versions": []
}