{
  "abstract": "Introduction: Early identification of mental health risks among university students requires high-quality, privacy-conscious dialogue data for developing and evaluating computational screening models. Existing synthetic datasets often lack the contextual nuance and diagnostic consistency needed to preserve clinically relevant psychological signals.\n\nMethods: We introduce Note2Narr, a neuro-symbolic framework for synthesizing high-fidelity training narratives from sparse counselor notes. A Dynamic Counseling Tree guides inquiry from broad topic exploration to in-depth probing of personal experiences. A Supervisor Agent equipped with a Chain of Psychological Clues audits the safety and consistency of generated narratives, while a Fictional Detail Generator incorporates diverse, disorder-neutral personal experiences. A Vendi Score-guided 1-to-X strategy adaptively allocates the number of narrative variants. Evaluation combines blinded human assessment, LLM-based assessment, student-disjoint downstream prediction, and a label-leakage audit with masking ablation.\n\nResults: The framework produced 981 multi-turn counseling dialogues comprising 11,145 question-answer turns from 224 source students. Blinded human comparisons with MDD-5K identified statistically significant improvements in Professionalism, Communication, Participation, Repetition, and Authenticity after Holm correction. Downstream text classifiers achieved macro-AUROC and macro-AUPRC values of up to 0.739 and 0.405, respectively. Masking explicit diagnostic cues changed macro-AUPRC by at most 0.005, suggesting that predictive utility was not driven solely by direct diagnostic wording.\n\nDiscussion: These findings support Note2Narr as a framework for constructing synthetic counseling corpora for privacy-conscious dialogue modeling and screening-oriented research. The results demonstrate learnable associations in synthetic narratives; prospective and external validation remains necessary before applied use.",
  "abstract_shown": true,
  "affiliations": [
    "HDU-ITMO Joint Institute, Hangzhou Dianzi University",
    "College of Computer Science and Technology, Zhejiang University of Technology"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hanrui Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Cheng Yang"
    },
    {
      "affs": [
        1
      ],
      "name": "Yilin Hu"
    },
    {
      "affs": [
        0
      ],
      "name": "Jiong Lin"
    },
    {
      "affs": [
        0
      ],
      "name": "Beining Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "Hanyin Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Fu Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bs4dw0p4n3v9z.bib",
  "cited_by": 0,
  "doi": "10.3389/fpsyt.2026.1948130",
  "fulltext_url": null,
  "id": "bs4dw0p4n3v9z",
  "issns": [
    "1664-0640"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fpsyt.2026.1948130/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": "2026-11-04",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/bs4dw0p4n3v9z.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T12:21:47Z",
      "native_id": "10.3389/fpsyt.2026.1948130",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fpsyt.2026.1948130/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:1664-0640",
      "subfield": "psychiatry"
    }
  ],
  "title": "Note2Narr: a neuro-symbolic multi-agent system for synthesizing high-fidelity training narratives from sparse counselor notes",
  "title_text": "Note2Narr: a neuro-symbolic multi-agent system for synthesizing high-fidelity training narratives from sparse counselor notes",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T00:21:27Z",
  "url": "https://research.draconitic.com/paper/bs4dw0p4n3v9z",
  "venue": "Frontiers in Psychiatry",
  "versions": []
}