paper-with-me

홈 › Papers

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

2025-06-20 · Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.2%) on our proposed theorem proving dataset. This issue arises from the limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 0.6% to 6.4%, and providing a curated dataset of 447 mathematical theorems in Lean 4 format for evaluation.

📄 PDF Abstract BibTeX arXiv:2506.17104

Code (0)

등록된 구현이 없습니다.

Tasks

Automated Theorem ProvingDiversityMathematical Reasoning

Similar Papers 제목 키워드 기반

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems

2025-08-12 · Yuren Hao, Xiang Wan, ChengXiang Zhai arxiv

In this paper, we introduce a systematic framework beyond conventional method to assess LLMs' mathematical-reasoning robustness by stress-testing them on advanced math problems that are mathematically equivalent but with…

Mathematical Reasoning

LPML: LLM-Prompting Markup Language for Mathematical Reasoning

2023-09-21 · Ryutaro Yamauchi, Sho Sonoda, Akiyoshi Sannai, Wataru Kumagai

In utilizing large language models (LLMs) for mathematical reasoning, addressing the errors in the reasoning and calculation present in the generated text by LLMs is a crucial challenge. In this paper, we propose a novel…

Mathematical Reasoning

Formal Language Knowledge Corpus for Retrieval Augmented Generation

2024-12-21 · Majd Zayyad, Yossi Adi

The integration of retrieval-augmented techniques with LLMs has shown promise in improving performance across various domains. However, their utility in tasks requiring advanced reasoning, such as generating and evaluati…

Logical ReasoningMathematical ProofsRAGRetrieval+1

Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics

2025-04-01 · Hamed Mahdavi, Alireza Hashemi, Majid Daliri, Pegah Mohammadipour 외

Recent advancements in large language models (LLMs) have shown impressive progress in mathematical reasoning tasks. However, current evaluation benchmarks predominantly focus on the accuracy of final answers, often overl…

MathMathematical Problem-SolvingMathematical Reasoning

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts

2025-04-25 · Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei 외

In this paper, we introduce PolyMath, a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels. Our benchmark ensures difficulty comprehensiveness, language diversity, an…

DiversityMathematical Reasoning