arXiv AI September 28, 2026 By Sang Bin Moon, Nicole Cho, Daniel Borrajo, Sumitra Ganesh, Abolfazl Hashemi

Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs

The paper introduces persona diversification as a set‑level conditioning strategy to reduce homogeneity in large language model outputs. It explores two design axes—selecting versus generating personas and space‑filling versus frontier‑seeking diversity—implementing four methods that span coverage and dispersion subset selections, uniform‑coverage sampling, and evolutionary persona generation. Experiments on tasks such as the Alternative Uses Task, Infinity‑Chat, and Divergent Association Task demonstrate significant gains in response diversity, originality, flexibility, and overall creativity, while maintaining high validity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Jul 31

Human diversity fuels collective creativity that large language models cannot simulate or sustain

arXiv:2607. 26899v1 Announce Type: cross Abstract: Diverse human groups produce diverse ideas, the raw material of innovation.

By Mengchen Dong, Hiromu Yakura

llms

arXiv AI

Jun 11

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

arXiv:2606. 11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential.

By Min Sen Tan, Zachary Kit Chun Choy, Syed Ali Redha Alsagoff, Nadya Yuki Wangsajaya, Mohor Banerjee, Swaagat Bikash Saikia, Alvin Chan

llms rag agents benchmarks

Hugging Face Trending Papers

Jul 29

Human diversity fuels collective creativity that large language models cannot simulate or sustain

Diverse human groups produce diverse ideas, the raw material of innovation. Generative AI challenges this engine twice over: everyday AI assistance may homogenize what diverse people create, and AI-simulated diversity may replace the people altogether.

llms

arXiv AI

Aug 21

Are LLMs becoming similarly creative? Evidence from three years of models

arXiv:2608. 19437v1 Announce Type: cross Abstract: Many benchmarks track Large Language Model (LLM) performance on tasks with verifiable answers, but less is known about how LLM performance is evolving on open-ended tasks, where creativity, originality and diversity may matter as much as quality.

By Nirav Patel, Josiah Crossman, Eva Aggarwal, Emily Wenger

llms rag benchmarks

Hugging Face Trending Papers

Jun 10

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks.

llms rag agents benchmarks

arXiv AI

Sep 15

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infer...

By Jiayi Yuan, Hangoo Kang, James Jihao Liu, Yejin Choi, Vikram Iyer, Liwei Jiang, Natasha Jaques

llms agents reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Human diversity fuels collective creativity that large language models cannot simulate or sustain

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Human diversity fuels collective creativity that large language models cannot simulate or sustain

Are LLMs becoming similarly creative? Evidence from three years of models

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning