Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910272060391424 |
|---|---|
| author | Wang, Junling Chen, Boqi Do, Heejin Akhtar, Mubashara Wang, April Yi Sachan, Mrinmaya |
| author_facet | Wang, Junling Chen, Boqi Do, Heejin Akhtar, Mubashara Wang, April Yi Sachan, Mrinmaya |
| contents | AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31212 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education Wang, Junling Chen, Boqi Do, Heejin Akhtar, Mubashara Wang, April Yi Sachan, Mrinmaya Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models. |
| title | Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.31212 |