Fostering children’s creativity through LLM-driven storytelling with a social robot
Maha Elgarf, Hanan Salam, Christopher Peters · 2024
Read Fostering children’s creativity through LLM-driven storytelling with a social robot by Maha Elgarf, Hanan Salam, Christopher Peters (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11671368.txt.
Description
Maha Elgarf, Hanan Salam, and Christopher Peters test a storytelling robot in a 2024 study on children's creativity. Creative skill often drops once children start school, where set answers crowd out imagination. Social robots in classrooms, in contrast, have shown promise for lifting learning.
A large language model was tuned to make a robot tell stories in a creative mode or a plain mode. Children then made stories with the robot in two studies. Their work was scored on four marks: how many ideas flowed, how varied they were, how much detail grew, and how original the turns were. The setup tests whether a robot's style can spark a child's own.
Catalog record
| CREATOR | Maha Elgarf, Hanan Salam, Christopher Peters |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |