{
  "abstract": "Patient-reported and clinically documented narratives often contain informal, fragmented and linguistically heterogeneous expressions, complicating medical concept normalization (MCN) and frequently necessitating pre-processing before terminology mapping. Despite rapid advances in biomedical language modeling, the comparative utility of representation models for MCN and their integration with instruction-tuned LLMs in automated normalization workflows remain underexplored. In this study, we systematically benchmarked 15 general, biomedical and clinical transformer-based representation models together with 12 instruction-tuned LLMs across 12,713 instances from five established datasets: TAC2017_ADR, TwADR-L, TwiMed, CADEC and SMM4H2017. Representation models were evaluated using embedding-based semantic retrieval, whereas instruction-tuned LLMs were assessed as upstream text-correction modules. SapBERT achieved the highest Top-5 accuracy among representation models, reaching 63.8% for SNOMED CT and 58.0% for MedDRA without correction. Qwen 2 Instruct was selected as the preferred corrector on the basis of its favorable balance between Top-1 normalization performance and computational efficiency relative to substantially larger models, including Llama 3.1 Instruct (70B). Incorporation of Qwen 2 Instruct increased Top-5 accuracy to 69.4% for SNOMED CT and 63.2% for MedDRA. The resulting framework accepts heterogeneous short medical expressions without manual input pre-processing and automatically performs text refinement, semantic retrieval and terminology mapping to standardized concepts and vocabulary codes. These findings establish a benchmark-guided, scalable framework for automated medical terminology standardization.",
  "abstract_shown": true,
  "affiliations": [
    "CSIR-Institute of Genomics and Integrative Biology"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "A. Verma"
    },
    {
      "name": "Abhijay"
    },
    {
      "name": "M. Vangani"
    },
    {
      "name": "S. Prakash"
    },
    {
      "affs": [
        0
      ],
      "name": "K. Chaudhary"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cxaw5h46rqacb.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.19.752843",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.19.752843v1.full",
  "id": "cxaw5h46rqacb",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.19.752843v1",
  "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": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Biomedical Text Mining and Ontologies"
    ]
  ],
  "openalex": "W7213984034",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.19.752843v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cxaw5h46rqacb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:37Z",
      "native_id": "10.64898/2026.09.19.752843",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.19.752843v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "A Comparative Benchmark of Biomedical Language Models for Concept Normalization from Real-World Text",
  "title_text": "A Comparative Benchmark of Biomedical Language Models for Concept Normalization from Real-World Text",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:37Z",
  "url": "https://research.draconitic.com/paper/cxaw5h46rqacb",
  "venue": "bioRxiv",
  "versions": []
}