Uncovering Grounding IDs: How External Cues Shape Multimodal Binding
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_ | 1866910032284614656 |
|---|---|
| author | Hasani, Hosein Izadi, Amirmohammad Askari, Fatemeh Bagherian, Mobin Mohammadian, Sadegh Izadi, Mohammad Baghshah, Mahdieh Soleymani |
| author_facet | Hasani, Hosein Izadi, Amirmohammad Askari, Fatemeh Bagherian, Mobin Mohammadian, Sadegh Izadi, Mohammad Baghshah, Mahdieh Soleymani |
| contents | Large vision-language models (LVLMs) show strong performance across multimodal benchmarks but remain limited in structured reasoning and precise grounding. Recent work has demonstrated that adding simple visual structures, such as partitions and annotations, improves accuracy, yet the internal mechanisms underlying these gains remain unclear. We investigate this phenomenon and propose the concept of Grounding IDs, latent identifiers induced by external cues that bind objects to their designated partitions across modalities. Through representation analysis, we find that these identifiers emerge as consistent within-partition alignment in embedding space and reduce the modality gap between image and text. Causal interventions further confirm that these identifiers mediate binding between objects and symbolic cues. We show that Grounding IDs strengthen attention between related components, which in turn improves cross-modal grounding and reduces hallucinations. Taken together, our results identify Grounding IDs as a key symbolic mechanism that explains how external cues enhance multimodal binding and offer both interpretability and practical improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncovering Grounding IDs: How External Cues Shape Multimodal Binding Hasani, Hosein Izadi, Amirmohammad Askari, Fatemeh Bagherian, Mobin Mohammadian, Sadegh Izadi, Mohammad Baghshah, Mahdieh Soleymani Computer Vision and Pattern Recognition Artificial Intelligence Large vision-language models (LVLMs) show strong performance across multimodal benchmarks but remain limited in structured reasoning and precise grounding. Recent work has demonstrated that adding simple visual structures, such as partitions and annotations, improves accuracy, yet the internal mechanisms underlying these gains remain unclear. We investigate this phenomenon and propose the concept of Grounding IDs, latent identifiers induced by external cues that bind objects to their designated partitions across modalities. Through representation analysis, we find that these identifiers emerge as consistent within-partition alignment in embedding space and reduce the modality gap between image and text. Causal interventions further confirm that these identifiers mediate binding between objects and symbolic cues. We show that Grounding IDs strengthen attention between related components, which in turn improves cross-modal grounding and reduces hallucinations. Taken together, our results identify Grounding IDs as a key symbolic mechanism that explains how external cues enhance multimodal binding and offer both interpretability and practical improvements. |
| title | Uncovering Grounding IDs: How External Cues Shape Multimodal Binding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.24072 |