Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs
cs.CL, cs.AI, stat.ML
Submitted: 2026-09-24
Updated: 2026-09-24
Terminology
Sources
- LLM Social Simulations Are a Promising Research Method
- CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
- Art or Artifice? Large Language Models and the False Promise of Creativity
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- Scaling Synthetic Data Creation with 1,000,000,000 Personas
- CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativity
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- Understanding the Effects of RLHF on LLM Generalisation and Diversity
- Learning Determinantal Point Processes
- LLM Generated Persona is a Promise with a Catch
- AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
- Illuminating search spaces by mapping elites
- Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts
- CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse
- Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
- Contrastive Search Is What You Need For Neural Text Generation
- Base Models Beat Aligned Models at Randomness and Creativity
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering