From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs

arXiv:2601.03682v2 Announce Type: replace Abstract: Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation, focusing on logical relationship understanding, which is a core capability underlying genuine logical reasoning, and reveal that errors related to this capability account for over 90% of incorrect predictions, with Chain-of-Thought Supervised Fine-Tuning (CoT-SFT) failing to substantially reduce these errors. To address this bottleneck, we propose First-Step Logical Reasoning (FSLR), a lightweight training framework targeting logical relationship understanding. Our key insight is that the first planning step-identifying which variables to use and which operation to apply-encourages the model to derive logical relationships directly from the problem statement. By training models on this isolated step, FSLR provides explicit supervision for logical relationship understanding, unlike CoT-SFT which implicitly embeds such relationships within complete solution trajectories. Extensive experiments across multiple models and datasets demonstrate that FSLR consistently outperforms CoT-SFT under both in-distribution and out-of-distribution settings, with average improvements of 3.2% and 4.6%, respectively. Moreover, FSLR achieves 4-6x faster training and reduces training token consumption by over 80%.

Related

• Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
• Beyond Translation: Evaluating Mathematical Reasoning Capabilities of LLMs in Sinhala and Tamil
• Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
• Do LLMs Encode Functional Importance of Reasoning Tokens?
• Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms

Source: arXiv cs.CL | 2026-04-21