按年被提到
20242024 · 1 次2026
数学、逻辑与理论›AI 数学与定理证明·arXiv:2404.12534 · cs.AI

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean

Peiyang Song, Kaiyu Yang, Anima Anandkumar · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-09-12 · 最近 2025-05-23
2不同的人
2活跃月份
2讨论串
23被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Neural theorem proving combines large language models (LLMs) with proof assistants such as Lean, where the correctness of formal proofs can be rigorously verified, leaving no room for hallucination. With existing neural theorem provers pretrained on a fixed collection of data and offering valuable suggestions at times, it is challenging for them to continually prove novel theorems in a fully autonomous mode, where human insights may be critical. In this paper, we explore LLMs as copilots that assist humans in proving theorems. We introduce Lean Copilot, a general framework for running LLM inference natively in Lean. It enables programmers to build various LLM-based proof automation tools that integrate seamlessly into the workflow of Lean users. Lean users can use our pretrained models or bring their own ones that run either locally (with or without GPUs) or on the cloud. Using Lean Copilot, we build LLM-based tools that suggest proof steps, complete proof goals, and select relevant premises. Experimental results on the Mathematics in Lean textbook demonstrate the effectiveness of our method compared to existing rule-based proof automation in Lean (aesop). When assisting humans, Lean Copilot requires only 2.08 manually-entered proof steps on average (3.86 required by aesop); when automating the theorem proving process, Lean Copilot automates 74.2% proof steps on average, 85% better than aesop (40.1%). We open source all code and artifacts under a permissive MIT license to facilitate further research.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ogogmad · 2025-05

“The article also suggests that you could use a proof-verifier like Lean instead. Using that capability to generate synthetic data on which to train helps too. Very large context windows have been known to help with programming, and should help with mathematical reasoning too. None of this gives you AGI, I suppose, but the important thing is it makes LLMs …”

Adventures in Symbolic Algebra with Model Context Protocol原评论 ↗
被提交为 story · 1 次