发表机构
Metropolitan State University（大都会州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对用大语言模型解决数学猜想的研究，论证需补充披露所用提示与软件设置、要求成果形式化以利机器验证，且作者应提供直观解释的必要性。
AI 中文摘要
近期已有若干数学猜想通过大语言模型（LLMs）得到解决，数学界已针对此类成果的发表制定了相关规范与建议，但这些规范未涵盖获取成果所用提示（prompts）及精确软件设置的披露要求，也不要求成果以可经机器验证的形式进行形式化。本文认为这两点均至关重要；此外，由于LLMs得出的成果可能难以理解，人类作者有责任构建直观的解释。
英文摘要
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.
Comments5 pages
