Meet DeepPersona: Scaling Realistic Synthetic Personas
DeepPersona in a nutshell
Researchers built a generative engine that creates richly detailed, realistic synthetic personas for AI—without using private personal data.
- Deeper profiles: Each persona includes hundreds of structured attributes and about 1 MB of narrative text—roughly 100x more detail than prior work.
- Big taxonomy: A hierarchy of hundreds of human attributes, mined from thousands of real user-ChatGPT conversations, guides coherent persona creation.
- Validated gains: 32% higher attribute diversity and 44% greater profile uniqueness versus top baselines.
- Better downstream performance: Improved GPT-4.1-mini’s personalized Q&A accuracy by 11.6% (across 10 metrics) and narrowed the gap between simulated and real survey responses by 31.7%; Big Five gap reduced by 17%.
Why this matters: DeepPersona offers a scalable, privacy-free way to study human-like behavior, test policies, and build more personalized, aligned AI—without collecting sensitive personal data.
Paper: http://arxiv.org/abs/2511.07338v1
Register: https://www.AiFeta.com
AI LLM SyntheticData SyntheticPersonas Personalization AgentSimulation Alignment Research
