Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913867241619456 |
|---|---|
| author | Sarto, Sara Cornia, Marcella Cucchiara, Rita |
| author_facet | Sarto, Sara Cornia, Marcella Cucchiara, Rita |
| contents | The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable evaluation metrics. This survey provides a comprehensive overview of advancements in image captioning evaluation, analyzing the evolution, strengths, and limitations of existing metrics. We assess these metrics across multiple dimensions, including correlation with human judgment, ranking accuracy, and sensitivity to hallucinations. Additionally, we explore the challenges posed by the longer and more detailed captions generated by MLLMs and examine the adaptability of current metrics to these stylistic variations. Our analysis highlights some limitations of standard evaluation approaches and suggests promising directions for future research in image captioning assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14604 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives Sarto, Sara Cornia, Marcella Cucchiara, Rita Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable evaluation metrics. This survey provides a comprehensive overview of advancements in image captioning evaluation, analyzing the evolution, strengths, and limitations of existing metrics. We assess these metrics across multiple dimensions, including correlation with human judgment, ranking accuracy, and sensitivity to hallucinations. Additionally, we explore the challenges posed by the longer and more detailed captions generated by MLLMs and examine the adaptability of current metrics to these stylistic variations. Our analysis highlights some limitations of standard evaluation approaches and suggests promising directions for future research in image captioning assessment. |
| title | Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.14604 |