Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
Abstract: Mathematical reasoning has been challenging for large language models (LLMs). However, the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs.
Despite this progress, current approaches either necessitate extensive inference datasets for training or depend on few-shot methods that frequently compromise computational accuracy.
To address these fundamental limitations, we propose Step Guided Reasoning (SGR), a novel training-free adaptation framework that efficiently equips general-purpose pre-trained language models, such as Qwen2-72B-Instruct, with enhanced mathematical reasoning capabilities.
In this approach, LLMs reflect on small reasoning steps, similar to how humans deliberate and focus attention on what to do next. By incorporating this reflective process into the inference stage, LLMs can effectively guide their reasoning from one step to the next.
Through extensive experiments, we demonstrate the significant effect of \ourmethod in enhancing mathematical performance in state-of-the-art language models.
Qwen2-72B-Instruct outperforms its math-specific counterpart, Qwen2.5-72B-Math-Instruct, on MMLU-STEM with a score of 90.9%, compared to 87.3%. The average scores of Qwen2-7B-Instruct and Qwen2-72B-Instruct increase from 27. 1% to 36. 3% and from 36. 5% to 47. 4% in the math domain, respectively.
Paper Type: Long
Research Area: NLP Applications
Research Area Keywords: Language Modeling
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 4933
Loading