MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task

• URL: http://arxiv.org/abs/2502.11684v1
• Date: Mon, 17 Feb 2025 11:22:24 GMT
• Title: MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
• Authors: Yuchen Yan, Yongliang Shen, Yang Liu, Jin Jiang, Xin Xu, Mengdi Zhang, Jian Shao, Yueting Zhuang,
• Abstract summary: We introduce MathFimer, a novel framework for mathematical reasoning step expansion.<n>We develop a specialized model, MathFimer-7B, on our carefully curated NuminaMath-FIM dataset.<n>We then apply these models to enhance existing mathematical reasoning datasets by inserting detailed intermediate steps into their solution chains.
• Score: 49.355810887265925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematical problem-solving in LLMs, the quality of reasoning steps in training data fundamentally constrains the performance of the models. Recent studies has demonstrated that more detailed intermediate steps can enhance model performance, yet existing methods for step expansion either require more powerful external models or incur substantial computational costs. In this paper, we introduce MathFimer, a novel framework for mathematical reasoning step expansion inspired by the "Fill-in-the-middle" task from code completion. By decomposing solution chains into prefix-suffix pairs and training models to reconstruct missing intermediate steps, we develop a specialized model, MathFimer-7B, on our carefully curated NuminaMath-FIM dataset. We then apply these models to enhance existing mathematical reasoning datasets by inserting detailed intermediate steps into their solution chains, creating MathFimer-expanded versions. Through comprehensive experiments on multiple mathematical reasoning datasets, including MathInstruct, MetaMathQA and etc., we demonstrate that models trained on MathFimer-expanded data consistently outperform their counterparts trained on original data across various benchmarks such as GSM8K and MATH. Our approach offers a practical, scalable solution for enhancing mathematical reasoning capabilities in LLMs without relying on powerful external models or expensive inference procedures.

Related papers

• MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion [48.443460251524776]
  MathFusion is a novel framework that enhances mathematical reasoning through cross-problem instruction synthesis. MathFusion achieves substantial improvements in mathematical reasoning while maintaining high data efficiency.
  arXiv  Detail & Related papers  (2025-03-20T15:00:41Z)
• Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models [0.0]
  Large models pre-trained on high-quality data exhibit excellent performance across various reasoning tasks. Smaller student models learn from teacher models, and data augmentation, such as rephrasing questions. Despite these efforts, smaller models struggle with arithmetic computations, leading to errors in mathematical reasoning.
  arXiv  Detail & Related papers  (2025-02-18T13:43:06Z)
• Large Language Models for Mathematical Analysis [3.7325315394927023]
  This work addresses critical gaps in mathematical reasoning and contributes to advancing trustworthy AI.<n>We developed the DEMI-MathAnalysis dataset, comprising proof-based problems from mathematical analysis topics.<n>We also designed a guiding framework to rigorously enhance LLMs' ability to solve these problems.
  arXiv  Detail & Related papers  (2024-12-28T20:37:55Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Benchmarking Large Language Models for Math Reasoning Tasks [12.91916443702145]
  We compare seven state-of-the-art in-context learning algorithms for mathematical problem solving across five widely used mathematical datasets on four powerful foundation models.<n>Our results indicate that larger foundation models like GPT-4o and LLaMA 3-70B can solve mathematical reasoning independently from the concrete prompting strategy.<n>We open-source our benchmark code to support the integration of additional models in future research.
  arXiv  Detail & Related papers  (2024-08-20T13:34:17Z)
• InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning [13.728595670907136]
  We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. Fine-tuning experiments with open-source language and code models, such as Llama2 and CodeLlama, demonstrate the practical benefits of InfinityMATH.
  arXiv  Detail & Related papers  (2024-08-09T08:18:20Z)
• MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
  MindStar is a purely inference-based searching method for large language models. It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
  arXiv  Detail & Related papers  (2024-05-25T15:07:33Z)
• AlphaMath Almost Zero: Process Supervision without Process [6.318873143509028]
  We propose an innovative framework, AlphaMath, that bypasses the need for process annotations by leveraging Monte Carlo Tree Search (MCTS) This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning. The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-06T15:20:30Z)
• Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions [47.83142414018448]
  We focus on two popular reasoning tasks: arithmetic reasoning and code generation. We introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets. We show a significant performance drop across all the models against perturbed questions.
  arXiv  Detail & Related papers  (2024-01-17T18:13:07Z)
• Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning [75.74103236299477]
  Chain-of-thought prompting(CoT) and tool augmentation have been validated as effective practices for improving large language models. We propose a new approach that can deliberate the reasoning steps with tool interfaces, namely textbfDELI. Experimental results on CARP and six other datasets show that the proposed DELI mostly outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-06-04T17:02:59Z)
• Bayesian Quadrature on Riemannian Data Manifolds [79.71142807798284]
  A principled way to model nonlinear geometric structure inherent in data is provided. However, these operations are typically computationally demanding. In particular, we focus on Bayesian quadrature (BQ) to numerically compute integrals over normal laws. We show that by leveraging both prior knowledge and an active exploration scheme, BQ significantly reduces the number of required evaluations.
  arXiv  Detail & Related papers  (2021-02-12T17:38:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.