New paper: LLMs adopt behaviors from story characters most similar to themselves

niloofar_mire · x · 2026-09-16

Owain Evans' team published a new paper showing that training models on synthetic stories about humans only (no AI characters) still causes the assistant to adopt quirky behaviors from those characters in ordinary chat.

Key findings:

The author includes an analysis thread probing why the similarity effect occurs.

Related event: Story Imprinting: AI Assistants Absorb Traits from Similar Human Characters(5 posts)→

Original post →

More from Research

Research channel →