Saved in:
Bibliographic Details
Main Authors: Tian, Yang, Lu, Zheng, Gao, Mingqi, Liu, Zheng, Zhao, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16856
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911025446518784
author Tian, Yang
Lu, Zheng
Gao, Mingqi
Liu, Zheng
Zhao, Bo
author_facet Tian, Yang
Lu, Zheng
Gao, Mingqi
Liu, Zheng
Zhao, Bo
contents Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically significant challenge. While Vision-Language Models (VLMs) have made remarkable strides in various tasks, particularly those involving reasoning with evidence source from single image or text page, their ability to use cross-source information for reasoning remains an open problem. This work presents MMCR, a high-difficulty benchmark designed to evaluate VLMs' capacity for reasoning with cross-source information from scientific papers. The benchmark comprises 276 high-quality questions, meticulously annotated by humans across 7 subjects and 10 task types. Experiments with 18 VLMs demonstrate that cross-source reasoning presents a substantial challenge for existing models. Notably, even the top-performing model, GPT-4o, achieved only 48.55% overall accuracy, with only 20% accuracy in multi-table comprehension tasks, while the second-best model, Qwen2.5-VL-72B, reached 39.86% overall accuracy. Furthermore, we investigated the impact of the Chain-of-Thought (CoT) technique on cross-source reasoning and observed a detrimental effect on small models, whereas larger models demonstrated substantially enhanced performance. These results highlight the pressing need to develop VLMs capable of effectively utilizing cross-source information for reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers
Tian, Yang
Lu, Zheng
Gao, Mingqi
Liu, Zheng
Zhao, Bo
Computation and Language
Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically significant challenge. While Vision-Language Models (VLMs) have made remarkable strides in various tasks, particularly those involving reasoning with evidence source from single image or text page, their ability to use cross-source information for reasoning remains an open problem. This work presents MMCR, a high-difficulty benchmark designed to evaluate VLMs' capacity for reasoning with cross-source information from scientific papers. The benchmark comprises 276 high-quality questions, meticulously annotated by humans across 7 subjects and 10 task types. Experiments with 18 VLMs demonstrate that cross-source reasoning presents a substantial challenge for existing models. Notably, even the top-performing model, GPT-4o, achieved only 48.55% overall accuracy, with only 20% accuracy in multi-table comprehension tasks, while the second-best model, Qwen2.5-VL-72B, reached 39.86% overall accuracy. Furthermore, we investigated the impact of the Chain-of-Thought (CoT) technique on cross-source reasoning and observed a detrimental effect on small models, whereas larger models demonstrated substantially enhanced performance. These results highlight the pressing need to develop VLMs capable of effectively utilizing cross-source information for reasoning.
title MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers
topic Computation and Language
url https://arxiv.org/abs/2503.16856