LLaVA‑Next‑Interleave Bench Dataset Overview

Dataset Details

Dataset Type: LLaVA‑Next‑Interleave Bench is a collection of multi‑image datasets gathered from public sources or generated via the GPT‑4V API. It is intended to assess the multi‑image processing capabilities of large multimodal models.

Dataset Date: The dataset was collected in April 2024, using both public data collection and GPT‑4V API generation.

Dataset Structure: After downloading and extracting, the following structure is present:

interleave_data ├── Split1 │ ├── ... │ └── ... │ ├── Split2 │ ├── ... │ └── ... ├── multi_image_in_domain.json ├── multi_image_out_domain.json └── multi_view_in_domain.json

License: The dataset is released under the Creative Commons Attribution 4.0 International license and must comply with OpenAI policy.

Issues and Feedback: For questions or comments, please contact fliay@connect.ust.hk.

Intended Use

Primary Intended Use: The LLaVA‑Next Interleave dataset is mainly for research on large multimodal models and chatbots.

Primary Intended Users: The dataset is aimed at researchers and enthusiasts in computer vision, natural language processing, machine learning, and artificial intelligence.