FormalMath500, MiniF2F-Solving, PutnamBench-Solving
收藏资源简介:
FormalMath500是MATH500基准的一部分的正式化;MiniF2F-Solving和PutnamBench-Solving是FTP基准MiniF2F和PutnamBench的改编版本。这些数据集旨在为正式问题解决提供基准,并用于评估FPS和D-FPS框架的性能。
FormalMath500 constitutes the formalization of a subset of the MATH500 benchmark. MiniF2F-Solving and PutnamBench-Solving are adapted variants of the MiniF2F and PutnamBench datasets belonging to the FTP benchmark. These datasets are developed to serve as benchmarks for formal mathematical problem solving, and are employed to evaluate the performance of the FPS and D-FPS frameworks.
数据集概述
基本信息
- 论文标题: Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
- 论文链接: https://arxiv.org/abs/2505.04528
- 数据集链接: https://huggingface.co/collections/purewhite42/formal-problem-solving-681b573aac8f09f308bb7c66
- 许可证: Apache 2.0
研究重点
- 问题解决的定义
- 在现有形式化定理证明(FTP)环境中进行过程验证的问题解决
主要贡献
- FPS: 利用FTP环境进行过程验证的问题解决
- D-FPS: 解耦求解和答案验证以实现更好的人机对齐
- RPE: 通过形式化验证确定答案正确性的符号方法
- 三个基准数据集: FormalMath500、MiniF2F-Solving和PutnamBench-Solving
基准数据集详情
FormalMath500
- 数据点: 387
- 分类:
- Algebra: 123
- Intermediate Algebra: 92
- Number Theory: 62
- Prealgebra: 65
- Precalculus: 45
MiniF2F-Solving
- 数据点: 375
- 分类:
- AIME: 30
- MATH-Algebra: 140
- AMC: 82
- IMO: 3
- MATH-Number Theory: 120
PutnamBench-Solving
- 数据点: 324
- 分类:
- Abstract Algebra: 9
- Algebra: 138
- Analysis: 122
- Combinatorics: 14
- Geometry: 28
- Linear Algebra: 25
- Number Theory: 49
- Probability: 8
- Set Theory: 4
数据结构
每个问题包含以下字段:
informal_problem: 自然语言描述的问题informal_answer: 自然语言描述的正确答案informal_solution: 自然语言描述的逐步解决方案header: 初始化形式化问题前应执行的代码intros: 独立变量和假设outros: 结论formal_answer: 形式化语言描述的正确答案formal_answer_type: 形式化语言描述的答案类型metainfo: 问题的元信息
评估方法
证明搜索(FPS)
- 使用模型: InternLM2.5-StepProver, LeanSTaR
- 评估指标: Solved, Proven, NE-Submitted
完整证明生成(FPS)
- 使用模型: DeepSeekProver-V1.5, TheoremLlama
- 评估指标: Solved, Proven, NE-Submitted
提示方法(D-FPS)
- 方法: In-Context Learning, Hybrid CoT
- 使用模型: DeepSeek-V3
- 评估指标: Solved, NE-Submitted
基准性能
| Framework | Benchmark | Method | Model | Solved↑ | Proven↑ | NE-Submitted↓ |
|---|---|---|---|---|---|---|
| FPS | FormalMath500 | Proof Search | InternLM2.5-StepProver | 23.77% | 47.55% | 19.38% |
| Whole-Proof Generation | DeepSeekProver-V1.5 | 22.22% | 46.51% | 14.47% | ||
| D-FPS | FormalMath500 | ICL | DeepSeek-V3 | 13.70% | 0.00% |
引用
bibtex @misc{liu2025theoremprovingformulationframework, title={Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving}, author={Qi Liu and Xinhao Zheng and Renqiu Xia and Xingzhi Qi and Qinxiang Cao and Junchi Yan}, year={2025}, eprint={2505.04528}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2505.04528}, }




