What happens when an LLM never sees material beyond fifth grade?

A study titled "LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure" explores the effects of limiting a Language Model's (LLM) exposure to material beyond a fifth-grade level. Authored by Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thaddäus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, and Wieland Brendel, this research is set to be published in 2026. The paper, with eprint 2608.13545, investigates the implications of such controlled knowledge exposure on LLM development.