Saved in:
Bibliographic Details
Main Authors: Chuharski, Jake, Collins, Elias Rojas, Meringolo, Mark
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.16177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910758459146240
author Chuharski, Jake
Collins, Elias Rojas
Meringolo, Mark
author_facet Chuharski, Jake
Collins, Elias Rojas
Meringolo, Mark
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mining Math Conjectures from LLMs: A Pruning Approach
Chuharski, Jake
Collins, Elias Rojas
Meringolo, Mark
Artificial Intelligence
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.
title Mining Math Conjectures from LLMs: A Pruning Approach
topic Artificial Intelligence
url https://arxiv.org/abs/2412.16177