Numeric Information in Elementary School Texts Generated by LLMs vs Human Experts

Anastasia Smirnova, Erin S. Lee, Shiying Li


Abstract
We analyze GPT-4o’s ability to represent numeric information in texts for elementary school children and assess it with respect to the human baseline. We show that both humans and GPT-4o reduce the amount of numeric information when adapting informational texts for children but GPT-4o retains more complex numeric types than humans do.
Anthology ID:
2025.aimecon-main.20
Volume:
Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
Month:
October
Year:
2025
Address:
Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
Editors:
Joshua Wilson, Christopher Ormerod, Magdalen Beiting Parrish
Venue:
AIME-Con
SIG:
Publisher:
National Council on Measurement in Education (NCME)
Note:
Pages:
183–191
Language:
URL:
https://aclanthology.org/2025.aimecon-main.20/
DOI:
Bibkey:
Cite (ACL):
Anastasia Smirnova, Erin S. Lee, and Shiying Li. 2025. Numeric Information in Elementary School Texts Generated by LLMs vs Human Experts. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 183–191, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).
Cite (Informal):
Numeric Information in Elementary School Texts Generated by LLMs vs Human Experts (Smirnova et al., AIME-Con 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.aimecon-main.20.pdf