Needle In A Multimodal Haystack

Weiyun Wang, Shuibai Zhang, yiming ren, Duan Yuchen, Tiantong Li, Shuo Liu, Mengkang Hu, Zhe Chen, kaipeng, Lewei Lu, Xizhou Zhu, luoping1121, Yu Qiao, Jifeng Dai, SII - Wenqi Shao, wenhai.wang

Needle In A Multimodal Haystack: 55 upvotes on Hugging Face Daily Papers, #4 of 21 papers on 2024-06-17. Day-by-day upvote history.

With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is required to answer the questions according to different key information scattered throughout the given multimodal document. Evaluating the leading MLLMs on MM-NIAH, we observe that existing models still have significant room for improvement on these tasks, especially on vision-centric evaluation. We hope this work can provide a platform for further research on long multimodal document comprehension and contribute to the advancement of MLLMs. Code and benchmark are released at https://github.com/OpenGVLab/MM-NIAH.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.