Can Multimodal Large Language Model Think Analogically?

TL;DR

This paper investigates the analogical reasoning abilities of Multimodal Large Language Models (MLLMs), demonstrating their potential to understand and solve multimodal analogical problems through novel prompting methods and outperforming existing approaches.

Contribution

The paper introduces a unified prompt template and a method to leverage MLLM's reasoning capabilities, providing evidence of their analogical reasoning in multimodal contexts.

Findings

MLLM can effectively understand multimodal analogical reasoning problems.

Proposed methods outperform existing models on benchmark datasets.

Preliminary evidence supports MLLM's reasoning capabilities in multimodal tasks.

Abstract

Analogical reasoning, particularly in multimodal contexts, is the foundation of human perception and creativity. Multimodal Large Language Model (MLLM) has recently sparked considerable discussion due to its emergent capabilities. In this paper, we delve into the multimodal analogical reasoning capability of MLLM. Specifically, we explore two facets: \textit{MLLM as an explainer} and \textit{MLLM as a predictor}. In \textit{MLLM as an explainer}, we primarily focus on whether MLLM can deeply comprehend multimodal analogical reasoning problems. We propose a unified prompt template and a method for harnessing the comprehension capabilities of MLLM to augment existing models. In \textit{MLLM as a predictor}, we aim to determine whether MLLM can directly solve multimodal analogical reasoning problems. The experiments show that our approach outperforms existing methods on popular datasets, providing preliminary evidence for the analogical reasoning capability of MLLM.