PreprintCC0arXiv
Explanations, Prompts, and Formalizations: Arguments for New Norms in LLM-Enabled Mathematical Research
Abstract
As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.
Related
- Types of statistical arguments in empirical research in psychology
- Research profiles and the mathematical landscape: A grassroots proposal for mathematics with AI
- The Equational Theories Project: Advancing Collaborative Mathematical Research at Scale
- A Central Limit Theorem for High-Temperature SYK Model: A case study on mathematical research using AI and Lean
- Recursive Reasoning Exploration: Mathematical Research through Evolving Reasoning Graphs : case study: An Exact Certificate-Degree Theorem for Two-Term Tensor Decompositions : Phase III of the Math Instruments Program
BibTeX
@misc{boldt2026explanations,
title = {{Explanations, Prompts, and Formalizations: Arguments for New Norms in LLM-Enabled Mathematical Research}},
author = {Axel Boldt},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.29401},
eprint = {2608.29401},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.29401},
note = {CC0},
}
RIS
TY - UNPB
TI - Explanations, Prompts, and Formalizations: Arguments for New Norms in LLM-Enabled Mathematical Research
AU - Axel Boldt
PY - 2026
DA - 2026/08/29
PB - arXiv
DO - 10.48550/arxiv.2608.29401
UR - https://arxiv.org/abs/2608.29401
AB - As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.
ER -