MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
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_ | 1866911429088509952 |
|---|---|
| author | Cohen, Vanya Mooney, Raymond |
| author_facet | Cohen, Vanya Mooney, Raymond |
| contents | Entity state tracking is a necessary component of world modeling that requires maintaining coherent representations of entities over time. Previous work has benchmarked entity tracking performance in purely text-based tasks. We introduce MET-Bench, a multimodal entity tracking benchmark designed to evaluate vision-language models' ability to track entity states across modalities. Using two structured domains, we assess how effectively current models integrate textual and image-based state updates. Our findings reveal a significant performance gap between text-based and image-based entity tracking. We empirically show this discrepancy primarily stems from deficits in visual reasoning rather than perception. We further show that explicit text-based reasoning strategies improve performance, yet limitations remain in long-horizon multimodal tasks. We develop a reinforcement learning method to improve performance on MET-Bench. Applying our method to open-source VLMs achieves competitive performance with advanced closed models. Our results highlight the need for improved multimodal representations and reasoning techniques to bridge the gap between textual and visual entity tracking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10886 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models Cohen, Vanya Mooney, Raymond Computation and Language Entity state tracking is a necessary component of world modeling that requires maintaining coherent representations of entities over time. Previous work has benchmarked entity tracking performance in purely text-based tasks. We introduce MET-Bench, a multimodal entity tracking benchmark designed to evaluate vision-language models' ability to track entity states across modalities. Using two structured domains, we assess how effectively current models integrate textual and image-based state updates. Our findings reveal a significant performance gap between text-based and image-based entity tracking. We empirically show this discrepancy primarily stems from deficits in visual reasoning rather than perception. We further show that explicit text-based reasoning strategies improve performance, yet limitations remain in long-horizon multimodal tasks. We develop a reinforcement learning method to improve performance on MET-Bench. Applying our method to open-source VLMs achieves competitive performance with advanced closed models. Our results highlight the need for improved multimodal representations and reasoning techniques to bridge the gap between textual and visual entity tracking. |
| title | MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.10886 |