MathTrap

In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a new dataset MATHTRAP‡ by introducing carefully designed logical traps into the problem descriptions of MATH and GSM8K.

math

View on GitHub

60 Stars

0 Forks

60 Watchers

Python Language

apache-2.0 License

100 SrcLog Score

Cost to Build

$176.4K

Market Value

$261.2K

How is this calculated?

Growth over time

1 data points · 2026-04-10 → 2026-04-10

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about MathTrap

Question copied to clipboard

What is the tongjingqi/MathTrap GitHub project? Description: "In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a new dataset MATHTRAP‡ by introducing carefully designed logical traps into the problem descriptions of MATH and GSM8K.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone MathTrap

Clone via HTTPS

git clone https://github.com/tongjingqi/MathTrap.git

Clone via SSH

[email protected]:tongjingqi/MathTrap.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the MathTrap issue tracker:

Open GitHub Issues

Similar to MathTrap

freeCodeCamp freecodecamp.cn mathjs gpu.js sympy Surge simple-statistics mlcourse.ai libchaos cute_headers mathnet-numerics stdlib RandomKit mathquill osmnx math-php Euler stats phobos sage-archive-2023-02-01 Project-Euler-solutions swix pragmatapro expr-eval Sophus long.js primesieve libRmath.js symengine AlgebraicEngine-Fraction