Year: 2024
Type: conference-paper
Abstract: This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images. These challenges stem from the inductive (bottom-up) nature of existing debating schemes. To address the issue, we propose a deductive (top-down) debating approach called Blueprint Debate on Graphs (BDoG). In BDoG, debates are confined to a blueprint graph to prevent opinion trivialization through world-level summarization. Moreover, by storing evidence in branches within the graph, BDoG mitigates distractions caused by frequent but irrelevant concepts. Extensive experiments validate that BDoG is able to achieve state-of-the-art results in ScienceQA and MMBench with significant improvements over previous methods. The source code can be accessed at https://github.com/thecharm/BDoG.
Authors: Changmeng Zheng, Dayong Liang, Wengyu Zhang, Xiao-Yong Wei, Tat-Seng Chua, Qing Li
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G4857298105
OpenAlex ID: W4403791417