New BASE method cuts LLM math reasoning formalization costs by 5x

Researchers have developed a new method called BASE for improving the efficiency of answer selection in mathematical reasoning tasks using large language models (LLMs) and the formal proof assistant Lean. BASE reduces computational costs by formalizing a single base candidate answer and then editing it to derive the remaining candidate statements, rather than formalizing each independently. This approach, facilitated by a rewriter model named LEANSCRIBE, simultaneously enhances selection accuracy and significantly cuts down the number of autoformalizer calls, offering a Pareto improvement across various datasets and solvers. AI

IMPACT Reduces computational costs for LLM-based mathematical reasoning, potentially enabling more efficient verification and selection of answers.

RANK_REASON The cluster contains an academic paper detailing a new method for LLM-based mathematical reasoning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• large-language models
• Lean
• LEANSCRIBE

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →