MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models

Haoxuan Li, Zhengmao Yang, Yunshan Ma, Yi Bin, Yang Yang, Tat-Seng Chua

Abstract: We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has received less attention, particularly in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event forecasting, i.e. highlighting and complementary. Then, we develop a novel framework, named MM-Forecast. It employs an Image Function Identification module to recognize these functions as verbal descriptions using multimodal large language models (MLLMs), and subsequently incorporates these function descriptions into LLM-based forecasting models. To evaluate our approach, we construct a new multimodal dataset, MidEast-TE-mm, by extending an existing event dataset MidEast-TE with images. Empirical studies demonstrate that our MM-Forecast can correctly identify the image functions, and further more, incorporating these verbal function descriptions significantly improves the forecasting performance. The dataset, code, and prompt will be released upon acceptanc

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Generation] Multimedia Foundation Models

Relevance To Conference: The task of temporal event forecasting is a critical and challenging task. Previous conventional methods have dealt with textual modalities only, ignoring the visual information in historical events. Therefore, to the best of our knowledge, we are the first to comprehensively investigate Multimodal Event Forecasting and evaluate the impact of images in the temporal event forecasting.

Submission Number: 4901