A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning

Changmeng Zheng, Dayong Liang, Wengyu Zhang, Xiao-Yong Wei, Tat-Seng Chua +1 more
3/22/2024
cs.AIcs.CLcs.MA

Official code: thecharm/BDoG (19 stars, last commit 2024-12-05).

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.

View on arXivView PDF

Code Implementations(1)

thecharm/BDoGOfficial100%

Code for ACM MM 2024 paper "A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning"

193Shell, PythonAug 5, 20241 years ago

Similar Papers

Cite this paper

@article{zheng2024picture,
  title  = {A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning},
  author = {Changmeng Zheng and Dayong Liang and Wengyu Zhang and Xiao-Yong Wei and Tat-Seng Chua and Qing Li},
  year   = {2024},
  eprint = {2403.14972},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.14972v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.14972.svg)](https://codeofpaper.com/paper/2403.14972)

Discussion