{
  "abstract": "Language models often produce homogeneous responses to open-ended tasks; such homogeneity can spawn groupthink-the convergence of ideas toward a singular and potentially suboptimal decision. We formulate persona diversification as a set-level conditioning problem and study two orthogonal design choices: selecting versus generating personas, and space-filling versus frontier-seeking diversity. We instantiate this design space with four methods spanning coverage and dispersion subset selections, uniform-coverage sampling, and evolutionary persona generation. Evaluations on the Alternative Uses Task (AUT), Infinity-Chat, and Divergent Association Task (DAT) show the benefits of the proposed methods across tasks and creativity objectives. On AUT, evolutionary persona generation increases response diversity by 78.8%, originality by 26.1%, flexibility by 49.5%, and holistic creativity by 13.9% over task-only prompting, while maintaining 98.5% validity; on Infinity-Chat, it nearly doubles persona-induced response separation relative to random personas. Moreover, evolutionary personas compose with creativity-optimized prompting, further increasing its response diversity by 18.6% and creativity by 6.3%. These results establish persona-set geometry as a task-agnostic mechanism for eliciting divergent LLM outputs, and support persona diversification as a reusable complement to prompt optimization.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.30492",
  "author_total": 5,
  "authors": [
    {
      "name": "Sang Bin Moon"
    },
    {
      "name": "Nicole Cho"
    },
    {
      "name": "Daniel Borrajo"
    },
    {
      "name": "Sumitra Ganesh"
    },
    {
      "name": "Abolfazl Hashemi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2hba7phxhnqjs.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.30492",
  "fulltext_url": null,
  "id": "2hba7phxhnqjs",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.30492",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7214665513",
  "pdf_url": "https://arxiv.org/pdf/2609.30492",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2hba7phxhnqjs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:03Z",
      "native_id": "2609.30492",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.30492"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs",
  "title_text": "Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:03Z",
  "url": "https://research.draconitic.com/paper/2hba7phxhnqjs",
  "venue": "arXiv",
  "versions": []
}