paper-with-me

홈 › Papers

InternLM2.5-StepProver: Advancing Automated Theorem Proving via Expert Iteration on Large-Scale LEAN Problems

2024-10-21 · Zijian Wu, Suozhi Huang, Zhejian Zhou, Huaiyuan Ying, Jiayu Wang, Dahua Lin, Kai Chen

Large Language Models (LLMs) have emerged as powerful tools in mathematical theorem proving, particularly when utilizing formal languages such as LEAN. The major learning paradigm is expert iteration, which necessitates a pre-defined dataset comprising numerous mathematical problems. In this process, LLMs attempt to prove problems within the dataset and iteratively refine their capabilities through self-training on the proofs they discover. We propose to use large scale LEAN problem datasets Lean-workbook for expert iteration with more than 20,000 CPU days. During expert iteration, we found log-linear trends between solved problem amount with proof length and CPU usage. We train a critic model to select relatively easy problems for policy models to make trials and guide the model to search for deeper proofs. InternLM2.5-StepProver achieves open-source state-of-the-art on MiniF2F, Lean-Workbook-Plus, ProofNet, and Putnam benchmarks. Specifically, it achieves a pass of 65.9% on the MiniF2F-test and proves (or disproves) 17.0% of problems in Lean-Workbook-Plus which shows a significant improvement compared to only 9.5% of problems proved when Lean-Workbook-Plus was released. We open-source our models and searched proofs at https://github.com/InternLM/InternLM-Math and https://huggingface.co/datasets/internlm/Lean-Workbook.

📄 PDF Abstract BibTeX arXiv:2410.15700

Code (1)

internlm/internlm-math 공식 구현 pytorch

Tasks

Automated Theorem ProvingCPUMath

Similar Papers 제목 키워드 기반

Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving

2026-05-12 · Shuo Xu, Jiakun Zhang, Junyu Lai, Chun Cao 외 arxiv

Automated theorem proving with large language models in Lean 4 is commonly approached through either step-level tactic prediction with tree search or whole-proof generation. These two paradigms represent opposite granula…

Automated Theorem Proving

LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover

2024-07-24 · Zijian Wu, Jiayu Wang, Dahua Lin, Kai Chen

Recently, large language models have presented promising results in aiding formal mathematical reasoning. However, their performance is restricted due to the scarcity of formal theorem-proving data, which requires additi…

Automated Theorem ProvingMathMathematical Reasoning

Lean Workbook: A large-scale Lean problem set formalized from natural language math problems

2024-06-06 · Huaiyuan Ying, Zijian Wu, Yihan Geng, Jiayu Wang 외

Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem p…

Automated Theorem ProvingMath

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

2025-05-29 · Ziyin Zhang, Jiahao Xu, Zhiwei He, Tian Liang 외

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems t…

Automated Theorem ProvingMathematical Reasoning

LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation

2025-05-17 · Junyu Lai, Jiakun Zhang, Shuo Xu, Taolue Chen 외

Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, …

Automated Theorem ProvingSynthetic Data Generation