Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yichi, Chen, Zhuo, Guo, Lingbing, Zhang, Wen, Chen, Huajun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909000376778752
author Zhang, Yichi
Chen, Zhuo
Guo, Lingbing
Zhang, Wen
Chen, Huajun
author_facet Zhang, Yichi
Chen, Zhuo
Guo, Lingbing
Zhang, Wen
Chen, Huajun
contents Understanding and reasoning with abstractive information from the visual modality presents significant challenges for current multi-modal large language models (MLLMs). Among the various forms of abstractive information, Multi-Modal Relational Knowledge (MMRK), which represents abstract relational structures between multi-modal entities using node-edge formats, remains largely under-explored. In particular, STructured and Abstractive Reasoning (STAR) on such data has received little attention from the research community. To bridge the dual gaps in large-scale high-quality data and capability enhancement methodologies, this paper makes the following key contributions: (i). An automatic STAR data engine capable of synthesizing images with MMRK to build multi-modal instruction data with reliable chain-of-thought thinking for various STAR tasks and (ii). A comprehsive two-stage capability enhancement training framework, accompanied by a suite of evaluation protocols tailored to different STAR tasks. Based upon these contributions, we introduce STAR-64K, a dataset comprising 64K high-quality multi-modal instruction samples, and conduct experiments across 5 open-source MLLMs. Experimental results show that our two-stage enhancement framework enables smaller 3B/7B models to significantly outperform GPT-4o in STAR. Additionally, we provide in-depth analysis regarding the effectiveness of various designs, data transferability, and scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images
Zhang, Yichi
Chen, Zhuo
Guo, Lingbing
Zhang, Wen
Chen, Huajun
Computer Vision and Pattern Recognition
Computation and Language
Understanding and reasoning with abstractive information from the visual modality presents significant challenges for current multi-modal large language models (MLLMs). Among the various forms of abstractive information, Multi-Modal Relational Knowledge (MMRK), which represents abstract relational structures between multi-modal entities using node-edge formats, remains largely under-explored. In particular, STructured and Abstractive Reasoning (STAR) on such data has received little attention from the research community. To bridge the dual gaps in large-scale high-quality data and capability enhancement methodologies, this paper makes the following key contributions: (i). An automatic STAR data engine capable of synthesizing images with MMRK to build multi-modal instruction data with reliable chain-of-thought thinking for various STAR tasks and (ii). A comprehsive two-stage capability enhancement training framework, accompanied by a suite of evaluation protocols tailored to different STAR tasks. Based upon these contributions, we introduce STAR-64K, a dataset comprising 64K high-quality multi-modal instruction samples, and conduct experiments across 5 open-source MLLMs. Experimental results show that our two-stage enhancement framework enables smaller 3B/7B models to significantly outperform GPT-4o in STAR. Additionally, we provide in-depth analysis regarding the effectiveness of various designs, data transferability, and scalability.
title Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2510.21828