Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.12503 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911316825866240 |
|---|---|
| author | Ye, Mingrui Zheng, Chanjin Yu, Zengyi Xiang, Chenyu Zhao, Zhixue Yuan, Zheng Yannakoudakis, Helen |
| author_facet | Ye, Mingrui Zheng, Chanjin Yu, Zengyi Xiang, Chenyu Zhao, Zhixue Yuan, Zheng Yannakoudakis, Helen |
| contents | Multimodal Large Language Models (MLLMs) show remarkable progress across many visual-language tasks; however, their capacity to evaluate artistic expression remains limited. Aesthetic concepts are inherently abstract and open-ended, and multimodal artwork annotations are scarce. We introduce KidsArtBench, a new benchmark of over 1k children's artworks (ages 5-15) annotated by 12 expert educators across 9 rubric-aligned dimensions, together with expert comments for feedback. Unlike prior aesthetic datasets that provide single scalar scores on adult imagery, KidsArtBench targets children's artwork and pairs multi-dimensional annotations with comment supervision to enable both ordinal assessment and formative feedback. Building on this resource, we propose an attribute-specific multi-LoRA approach, where each attribute corresponds to a distinct evaluation dimension (e.g., Realism, Imagination) in the scoring rubric, with Regression-Aware Fine-Tuning (RAFT) to align predictions with ordinal scales. On Qwen2.5-VL-7B, our method increases correlation from 0.468 to 0.653, with the largest gains on perceptual dimensions and narrowed gaps on higher-order attributes. These results show that educator-aligned supervision and attribute-aware training yield pedagogically meaningful evaluations and establish a rigorous testbed for sustained progress in educational AI. We release data and code with ethics documentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12503 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs Ye, Mingrui Zheng, Chanjin Yu, Zengyi Xiang, Chenyu Zhao, Zhixue Yuan, Zheng Yannakoudakis, Helen Artificial Intelligence Multimodal Large Language Models (MLLMs) show remarkable progress across many visual-language tasks; however, their capacity to evaluate artistic expression remains limited. Aesthetic concepts are inherently abstract and open-ended, and multimodal artwork annotations are scarce. We introduce KidsArtBench, a new benchmark of over 1k children's artworks (ages 5-15) annotated by 12 expert educators across 9 rubric-aligned dimensions, together with expert comments for feedback. Unlike prior aesthetic datasets that provide single scalar scores on adult imagery, KidsArtBench targets children's artwork and pairs multi-dimensional annotations with comment supervision to enable both ordinal assessment and formative feedback. Building on this resource, we propose an attribute-specific multi-LoRA approach, where each attribute corresponds to a distinct evaluation dimension (e.g., Realism, Imagination) in the scoring rubric, with Regression-Aware Fine-Tuning (RAFT) to align predictions with ordinal scales. On Qwen2.5-VL-7B, our method increases correlation from 0.468 to 0.653, with the largest gains on perceptual dimensions and narrowed gaps on higher-order attributes. These results show that educator-aligned supervision and attribute-aware training yield pedagogically meaningful evaluations and establish a rigorous testbed for sustained progress in educational AI. We release data and code with ethics documentation. |
| title | KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.12503 |