WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning

TL;DR

WorldQA is a challenging multimodal video question-answering dataset that emphasizes long-chain reasoning and world knowledge, revealing current models' limitations and guiding future improvements in multimodal understanding.

Contribution

The paper introduces WorldQA, a novel dataset with long-chain reasoning and multimodal inputs, and proposes WorldRetriever, a model that synthesizes expert knowledge for improved reasoning.

Findings

WorldRetriever achieves 70% of human performance on multiple-choice questions.

Models perform worse with more frames, unlike humans who improve.

Long-chain reasoning significantly challenges current multimodal models.

Abstract

Multimodal information, together with our knowledge, help us to understand the complex and dynamic world. Large language models (LLM) and large multimodal models (LMM), however, still struggle to emulate this capability. In this paper, we present WorldQA, a video understanding dataset designed to push the boundaries of multimodal world models with three appealing properties: (1) Multimodal Inputs: The dataset comprises 1007 question-answer pairs and 303 videos, necessitating the analysis of both auditory and visual data for successful interpretation. (2) World Knowledge: We identify five essential types of world knowledge for question formulation. This approach challenges models to extend their capabilities beyond mere perception. (3) Long-Chain Reasoning: Our dataset introduces an average reasoning step of 4.45, notably surpassing other videoQA datasets. Furthermore, we introduce WorldRetriever, an agent designed to synthesize expert knowledge into a coherent reasoning chain, thereby facilitating accurate responses to WorldQA queries. Extensive evaluations of 13 prominent LLMs and LMMs reveal that WorldRetriever, although being the most effective model, achieved only 70% of humanlevel performance in multiple-choice questions. This finding highlights the necessity for further advancement in the reasoning and comprehension abilities of models. Our experiments also yield several key insights. For instance, while humans tend to perform better with increased frames, current LMMs, including WorldRetriever, show diminished performance under similar conditions. We hope that WorldQA,our methodology, and these insights could contribute to the future development of multimodal world models.