EasyMath: A 0-shot Math Benchmark for SLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915295583535104 |
|---|---|
| author | Karki, Drishya Kamphuis, Michiel Frey, Angelecia |
| author_facet | Karki, Drishya Kamphuis, Michiel Frey, Angelecia |
| contents | EasyMath is a compact benchmark for practical math reasoning in small language models. It covers thirteen categories, from basic arithmetic and order of operations to word problems, algebraic expressions, edge cases, and omits specialist topics. We tested 23 models (14M to 4B parameters) using exact, numerical, and symbolic checks on free-form answers in a zero-shot setting. Accuracy rises with size and training, chain-of-thought adds modest gains, and consistency improves at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EasyMath: A 0-shot Math Benchmark for SLMs Karki, Drishya Kamphuis, Michiel Frey, Angelecia Computation and Language Artificial Intelligence Machine Learning I.2.6; I.2.7 EasyMath is a compact benchmark for practical math reasoning in small language models. It covers thirteen categories, from basic arithmetic and order of operations to word problems, algebraic expressions, edge cases, and omits specialist topics. We tested 23 models (14M to 4B parameters) using exact, numerical, and symbolic checks on free-form answers in a zero-shot setting. Accuracy rises with size and training, chain-of-thought adds modest gains, and consistency improves at scale. |
| title | EasyMath: A 0-shot Math Benchmark for SLMs |
| topic | Computation and Language Artificial Intelligence Machine Learning I.2.6; I.2.7 |
| url | https://arxiv.org/abs/2505.14852 |