JunyiYe/CreativeMath
[AAAI 2025] Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems
This project helps researchers and educators evaluate how creatively Large Language Models (LLMs) solve math problems. It takes a mathematical problem and a known solution, then assesses an LLM's ability to generate genuinely new and different solutions. Anyone involved in AI research, education, or curriculum development who wants to understand and improve AI's creative mathematical reasoning would find this useful.
No commits in the last 6 months.
Use this if you need to objectively measure the novelty and creativity of mathematical solutions proposed by different AI models, beyond just checking for correctness.
Not ideal if you are only interested in whether an LLM produces the correct answer to a math problem, or if you need a tool for general math problem-solving assistance.
Stars
13
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/JunyiYe/CreativeMath"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MMMU-Benchmark/MMMU
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal...
pat-jj/DeepRetrieval
[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome
lupantech/MathVista
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
x66ccff/liveideabench
[𝐍𝐚𝐭𝐮𝐫𝐞 𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬] 🤖💡 LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea...
ise-uiuc/magicoder
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct