Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models

Neeraj Gangwar, Suma Bhat, Nickvash Kani


Abstract
While large models pre-trained on high-quality data exhibit excellent performance on mathematical reasoning (e.g., GSM8k, MultiArith), it remains challenging to specialize smaller models for these tasks. Common approaches to address this challenge include knowledge distillation from large teacher models and data augmentation (e.g., rephrasing questions and generating synthetic solutions). Despite these efforts, smaller models struggle with arithmetic computations, leading to errors in mathematical reasoning. In this work, we leverage a synthetic arithmetic dataset generated programmatically to enhance the reasoning capabilities of smaller models. We investigate two key approaches to incorporate this dataset: (1) intermediate fine-tuning, in which a model is fine-tuned on the arithmetic dataset before training it on a reasoning dataset, and (2) integrating the arithmetic dataset into an instruction-tuning mixture, allowing the model to learn arithmetic skills alongside general instruction-following abilities. Our experiments on multiple reasoning benchmarks demonstrate that incorporating an arithmetic dataset, whether through targeted fine-tuning or within an instruction-tuning mixture, enhances models’ arithmetic capabilities, thereby improving their mathematical reasoning performance.
Anthology ID:
2026.lrec-1.398
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
5078–5094
Language:
External URL:
https://lrec.elra.info/lrec2026-main-398
DOI:
10.63317/35u36mdkj4r7
Bibkey:
Cite (ACL):
Neeraj Gangwar, Suma Bhat, and Nickvash Kani. 2026. Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5078–5094, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models (Gangwar et al., LREC 2026)
Copy Citation: