EmoLLM: Multimodal Emotional Understanding Meets Large Language Models

TL;DR

EmoLLM introduces a novel multimodal model and benchmark for understanding complex human emotions in images and videos, significantly improving emotional comprehension in large language models.

Contribution

The paper presents EmoLLM and EmoBench, pioneering tools for evaluating and enhancing emotional understanding in multimodal large language models.

Findings

EmoLLM improves emotional understanding performance by 12.1%.

Multi-perspective Visual Projection captures diverse emotional cues.

EmoPrompt effectively guides emotion reasoning.

Abstract

Multi-modal large language models (MLLMs) have achieved remarkable performance on objective multimodal perception tasks, but their ability to interpret subjective, emotionally nuanced multimodal content remains largely unexplored. Thus, it impedes their ability to effectively understand and react to the intricate emotions expressed by humans through multimodal media. To bridge this gap, we introduce EmoBench, the first comprehensive benchmark designed specifically to evaluate the emotional capabilities of MLLMs across five popular emotional tasks, using a diverse dataset of 287k images and videos paired with corresponding textual instructions. Meanwhile, we propose EmoLLM, a novel model for multimodal emotional understanding, incorporating with two core techniques. 1) Multi-perspective Visual Projection, it captures diverse emotional cues from visual data from multiple perspectives. 2) EmoPrompt, it guides MLLMs to reason about emotions in the correct direction. Experimental results demonstrate that EmoLLM significantly elevates multimodal emotional understanding performance, with an average improvement of 12.1% across multiple foundation models on EmoBench. Our work contributes to the advancement of MLLMs by facilitating a deeper and more nuanced comprehension of intricate human emotions, paving the way for the development of artificial emotional intelligence capabilities with wide-ranging applications in areas such as human-computer interaction, mental health support, and empathetic AI systems. Code, data, and model will be released.