ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities
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_ | 1866929720245878784 |
|---|---|
| author | Zheng, Chanjin Yu, Zengyi Jiang, Yilin Zhang, Mingzi Lu, Xunuo Jin, Jing Gao, Liteng |
| author_facet | Zheng, Chanjin Yu, Zengyi Jiang, Yilin Zhang, Mingzi Lu, Xunuo Jin, Jing Gao, Liteng |
| contents | Can Multimodal Large Language Models (MLLMs), with capabilities in perception, recognition, understanding, and reasoning, function as independent assistants in art evaluation dialogues? Current MLLM evaluation methods, which rely on subjective human scoring or costly interviews, lack comprehensive coverage of various scenarios. This paper proposes a process-oriented Human-Computer Interaction (HCI) space design to facilitate more accurate MLLM assessment and development. This approach aids teachers in efficient art evaluation while also recording interactions for MLLM capability assessment. We introduce ArtMentor, a comprehensive space that integrates a dataset and three systems to optimize MLLM evaluation. The dataset consists of 380 sessions conducted by five art teachers across nine critical dimensions. The modular system includes agents for entity recognition, review generation, and suggestion generation, enabling iterative upgrades. Machine learning and natural language processing techniques ensure the reliability of evaluations. The results confirm GPT-4o's effectiveness in assisting teachers in art evaluation dialogues. Our contributions are available at https://artmentor.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13832 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities Zheng, Chanjin Yu, Zengyi Jiang, Yilin Zhang, Mingzi Lu, Xunuo Jin, Jing Gao, Liteng Human-Computer Interaction Can Multimodal Large Language Models (MLLMs), with capabilities in perception, recognition, understanding, and reasoning, function as independent assistants in art evaluation dialogues? Current MLLM evaluation methods, which rely on subjective human scoring or costly interviews, lack comprehensive coverage of various scenarios. This paper proposes a process-oriented Human-Computer Interaction (HCI) space design to facilitate more accurate MLLM assessment and development. This approach aids teachers in efficient art evaluation while also recording interactions for MLLM capability assessment. We introduce ArtMentor, a comprehensive space that integrates a dataset and three systems to optimize MLLM evaluation. The dataset consists of 380 sessions conducted by five art teachers across nine critical dimensions. The modular system includes agents for entity recognition, review generation, and suggestion generation, enabling iterative upgrades. Machine learning and natural language processing techniques ensure the reliability of evaluations. The results confirm GPT-4o's effectiveness in assisting teachers in art evaluation dialogues. Our contributions are available at https://artmentor.github.io/. |
| title | ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2502.13832 |