List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917896032092160 |
|---|---|
| author | Yan, An Yang, Zhengyuan Wu, Junda Zhu, Wanrong Yang, Jianwei Li, Linjie Lin, Kevin Wang, Jianfeng McAuley, Julian Gao, Jianfeng Wang, Lijuan |
| author_facet | Yan, An Yang, Zhengyuan Wu, Junda Zhu, Wanrong Yang, Jianwei Li, Linjie Lin, Kevin Wang, Jianfeng McAuley, Julian Gao, Jianfeng Wang, Lijuan |
| contents | Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed via text tokens for easy reference. Despite the extraordinary performance from GPT-4V, we observe that other Multimodal Large Language Models (MLLMs) struggle to understand these visual tags. To promote the learning of SoM prompting for open-source models, we propose a new learning paradigm: "list items one by one," which asks the model to enumerate and describe all visual tags placed on the image following the alphanumeric orders of tags. By integrating our curated dataset with other visual instruction tuning datasets, we are able to equip existing MLLMs with the SoM prompting ability. Furthermore, we evaluate our finetuned SoM models on five MLLM benchmarks. We find that this new dataset, even in a relatively small size (10k-30k images with tags), significantly enhances visual reasoning capabilities and reduces hallucinations for MLLMs. Perhaps surprisingly, these improvements persist even when the visual tags are omitted from input images during inference. This suggests the potential of "list items one by one" as a new paradigm for training MLLMs, which strengthens the object-text alignment through the use of visual tags in the training stage. Finally, we conduct analyses by probing trained models to understand the working mechanism of SoM. Our code and data are available at \url{https://github.com/zzxslp/SoM-LLaVA}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16375 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs Yan, An Yang, Zhengyuan Wu, Junda Zhu, Wanrong Yang, Jianwei Li, Linjie Lin, Kevin Wang, Jianfeng McAuley, Julian Gao, Jianfeng Wang, Lijuan Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed via text tokens for easy reference. Despite the extraordinary performance from GPT-4V, we observe that other Multimodal Large Language Models (MLLMs) struggle to understand these visual tags. To promote the learning of SoM prompting for open-source models, we propose a new learning paradigm: "list items one by one," which asks the model to enumerate and describe all visual tags placed on the image following the alphanumeric orders of tags. By integrating our curated dataset with other visual instruction tuning datasets, we are able to equip existing MLLMs with the SoM prompting ability. Furthermore, we evaluate our finetuned SoM models on five MLLM benchmarks. We find that this new dataset, even in a relatively small size (10k-30k images with tags), significantly enhances visual reasoning capabilities and reduces hallucinations for MLLMs. Perhaps surprisingly, these improvements persist even when the visual tags are omitted from input images during inference. This suggests the potential of "list items one by one" as a new paradigm for training MLLMs, which strengthens the object-text alignment through the use of visual tags in the training stage. Finally, we conduct analyses by probing trained models to understand the working mechanism of SoM. Our code and data are available at \url{https://github.com/zzxslp/SoM-LLaVA}. |
| title | List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2404.16375 |