2024/12/09 by Jake Chuharski, Chuharski, Jake, Elias Rojas Collins +3
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Biology #Botany #Econometrics #FOS: Computer and information sciences #Mathematics #Mathematics, Computing, and Information Processing #Natural Language Processing Techniques #Open Education and E-Learning #Pruning
paper · pdf · doi:10.48550/arxiv.2412.16177
openalex publication_date 2024/12/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present a novel approach to generating mathematical conjectures using Large Language Models (LLMs). Focusing on the solubilizer, a relatively recent construct in group theory, we demonstrate how LLMs such as ChatGPT, Gemini, and Claude can be leveraged to generate conjectures. These conjectures are pruned by allowing the LLMs to generate counterexamples. Our results indicate that LLMs are capable of producing original conjectures that, while not groundbreaking, are either plausible or falsifiable via counterexamples, though they exhibit limitations in code execution.