From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities

Chaochao Lu¹  Chen Qian  Guodong Zheng  Hongxing Fan  Hongzhi Gao  Jie Zhang

Jing Shao^†  Jingyi Deng  Jinlan Fu²  Kexin Huang  Kunchang Li  Lijun Li

Limin Wang³  Lu Sheng4  Meiqi Chen  Ming Zhang  Qibing Ren  Sirui Chen  Tao Gui⁵

Wanli Ouyang  Yali Wang⁶  Yan Teng⁷  Yaru Wang  Yi Wang  Yinan He

Yingchun Wang⁷  Yixu Wang  Yongting Zhang  Yu Qiao^†  Yujiong Shen  Yurong Mou

Yuxi Chen  Zaibin Zhang  Zhelun Shi  Zhenfei Yin^∗  Zhipin Wang

Shanghai AI Laboratory

Abstract

Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications and the expectation of the broad public, even though the most powerful OpenAI's GPT-4 and Google's Gemini have been deployed. This paper strives to enhance understanding of the gap through the lens of a qualitative study on the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities: ie, text, code, image, and video, ultimately aiming to improve the transparency of MLLMs. We believe these properties are several representative factors that define the reliability of MLLMs, in supporting various downstream applications. To be specific, we evaluate the closed-source GPT-4 and Gemini and 6 open-source LLMs and MLLMs. Overall we evaluate 230 manually designed cases, where the qualitative results are then summarized into 12 scores (ie, 4 modalities times 3 properties). In total, we uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs, towards more reliable downstream multi-modal applications.