Is persona in LLMs more like selection (persona X get's activated) or more like voting (many personas that are vaguely relevant vote on what the model will say next)?
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{holtzman-persona-selection-or-2026,
author = {Holtzman, Ari},
title = {Persona Selection or Voting?},
year = {2026},
url = {https://hypogenic.ai/ideahub/idea/AJ84HAMNJZCHXILyOUJy}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!