LemmaHead: RAG Assisted Proof Generation Using Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913684497891328 |
|---|---|
| author | Yang, Tianbo Yan, Mingqi Zhao, Hongyi Yang, Tianshuo |
| author_facet | Yang, Tianbo Yan, Mingqi Zhao, Hongyi Yang, Tianshuo |
| contents | Developing the logic necessary to solve mathematical problems or write mathematical proofs is one of the more difficult objectives for large language models (LLMS). Currently, the most popular methods in literature consists of fine-tuning the model on written mathematical content such as academic publications and textbooks, so that the model can learn to emulate the style of mathematical writing. In this project, we explore the effectiveness of using retrieval augmented generation (RAG) to address gaps in the mathematical reasoning of LLMs. We develop LemmaHead, a RAG knowledge base that supplements queries to the model with relevant mathematical context, with particular focus on context from published textbooks. To measure our model's performance in mathematical reasoning, our testing paradigm focuses on the task of automated theorem proving via generating proofs to a given mathematical claim in the Lean formal language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LemmaHead: RAG Assisted Proof Generation Using Large Language Models Yang, Tianbo Yan, Mingqi Zhao, Hongyi Yang, Tianshuo Machine Learning Computation and Language Information Retrieval Developing the logic necessary to solve mathematical problems or write mathematical proofs is one of the more difficult objectives for large language models (LLMS). Currently, the most popular methods in literature consists of fine-tuning the model on written mathematical content such as academic publications and textbooks, so that the model can learn to emulate the style of mathematical writing. In this project, we explore the effectiveness of using retrieval augmented generation (RAG) to address gaps in the mathematical reasoning of LLMs. We develop LemmaHead, a RAG knowledge base that supplements queries to the model with relevant mathematical context, with particular focus on context from published textbooks. To measure our model's performance in mathematical reasoning, our testing paradigm focuses on the task of automated theorem proving via generating proofs to a given mathematical claim in the Lean formal language. |
| title | LemmaHead: RAG Assisted Proof Generation Using Large Language Models |
| topic | Machine Learning Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2501.15797 |