PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 5, 2025Open Access

Elementary Math Word Problem Generation using Large Language Models

View Full Paper
Ask AI
Bookmark
Share

Authors

NANimesh AriyarathneHBH. A. Nelumi BandaraYHYasith Heshan

Discussion

Loading...

Member takes

Overview

This system generates math word problems in various types for different grades, suggesting improvements for educational tools.

Key Points

  • The generated math word problems are high quality, with minimal spelling and grammar issues.
  • Automated evaluations indicated superior performance, yet LLMs still had challenges with adhering to grade and question type specifications.
  • Extensive experiments on different LLMs and prompting strategies were performed to enhance diversity and quality in problem generation.
  • Human feedback significantly contributed to the improvements in the performance of the generated math word problems.

Cite This Study

Ariyarathne et al. (2025) studied this question.

synapsesocial.com/papers/68bb4df56d6d5674bcd0223dhttps://doi.org/10.21203/rs.3.rs-6814693/v1
View Full Paper
Ask AI
Bookmark
Share