mlsanityData to 14 Oct 2026

Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs

arXiv 2609.30492 ↗First posted 24 Sep 2026cs.CL cs.AI stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 59 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

20 of 59 references.

References · 20

  1. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  2. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  3. 2015Illuminating search spaces by mapping elitescited by 425
  4. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 417
  5. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 396
  6. 2024A Roadmap to Pluralistic Alignmentcited by 184
  7. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  8. 2023Art or Artifice? Large Language Models and the False Promise of Creativitycited by 172
  9. 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)cited by 141
  10. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  11. 2025LLM Generated Persona is a Promise with a Catchcited by 81
  12. 2022Contrastive Search Is What You Need For Neural Text Generationcited by 59
8 more
  1. 2025Base Models Beat Aligned Models at Randomness and Creativitycited by 51
  2. 2024AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Textcited by 42
  3. 2023Probing the Creativity of Large Language Models: Can models produce divergent semantic association?cited by 33
  4. 2024CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraintscited by 24
  5. 2025Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerabilitycited by 20
  6. 2026Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contextscited by 6
  7. 2025CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativitycited by 4
  8. 2026CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapsecited by 2

Built on by

Not cited yet.