DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

• URL: http://arxiv.org/abs/2411.00836v1
• Date: Tue, 29 Oct 2024 17:29:19 GMT
• Title: DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models
• Authors: Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, Huan Zhang,
• Abstract summary: We introduce DynaMath, a dynamic visual math benchmark designed for in-depth assessment of Vision-Language Models (VLMs) DynaMath includes 501 high-quality, multi-topic seed questions, each represented as a Python program. Our results show that the worst-case model accuracy, defined as the percentage of correctly answered seed questions in all 10 variants, is significantly lower than the average-case accuracy.
• Score: 19.787224412654872
• License:
• Abstract: The rapid advancements in Vision-Language Models (VLMs) have shown great potential in tackling mathematical reasoning tasks that involve visual context. Unlike humans who can reliably apply solution steps to similar problems with minor modifications, we found that SOTA VLMs like GPT-4o can consistently fail in these scenarios, revealing limitations in their mathematical reasoning capabilities. In this paper, we investigate the mathematical reasoning robustness in VLMs and evaluate how well these models perform under different variants of the same question, such as changes in visual numerical values or function graphs. While several vision-based math benchmarks have been developed to assess VLMs' problem-solving capabilities, these benchmarks contain only static sets of problems and cannot easily evaluate mathematical reasoning robustness. To fill this gap, we introduce DynaMath, a dynamic visual math benchmark designed for in-depth assessment of VLMs. DynaMath includes 501 high-quality, multi-topic seed questions, each represented as a Python program. Those programs are carefully designed and annotated to enable the automatic generation of a much larger set of concrete questions, including many different types of visual and textual variations. DynaMath allows us to evaluate the generalization ability of VLMs, by assessing their performance under varying input conditions of a seed question. We evaluated 14 SOTA VLMs with 5,010 generated concrete questions. Our results show that the worst-case model accuracy, defined as the percentage of correctly answered seed questions in all 10 variants, is significantly lower than the average-case accuracy. Our analysis emphasizes the need to study the robustness of VLMs' reasoning abilities, and DynaMath provides valuable insights to guide the development of more reliable models for mathematical reasoning.

Related papers

• AutoBench-V: Can Large Vision-Language Models Benchmark Themselves? [55.14033256706175]
  Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. We introduce AutoBench-V, an automated framework for serving evaluation on demand. Through an extensive evaluation of seven popular LVLMs across five demanded user inputs, the framework shows effectiveness and reliability.
  arXiv  Detail & Related papers  (2024-10-28T17:55:08Z)
• Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark [53.61633384281524]
  PolyMATH is a benchmark aimed at evaluating the general cognitive reasoning abilities of MLLMs. The best scores achieved on PolyMATH are 41%, 36%, and 27%, obtained by Claude-3.5 Sonnet, GPT-4o and Gemini-1.5 Pro respectively. A further fine-grained error analysis reveals that these models struggle to understand spatial relations and perform drawn-out, high-level reasoning.
  arXiv  Detail & Related papers  (2024-10-06T20:35:41Z)
• DARE: Diverse Visual Question Answering with Robustness Evaluation [16.87867803628065]
  Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models. They struggle with a number of crucial vision-language (VL) reasoning abilities such as counting and spatial reasoning. We introduce DARE, Diverse Visual Question Answering with Robustness Evaluation.
  arXiv  Detail & Related papers  (2024-09-26T16:31:50Z)
• MathScape: Evaluating MLLMs in multimodal Math Scenarios through a Hierarchical Benchmark [29.9945601202065]
  We propose MathScape, a new benchmark that emphasizes the understanding and application of combined visual and textual information. MathScape is designed to evaluate photo-based math problem scenarios, assessing the theoretical understanding and application ability of MLLMs. We conduct a multi-dimensional evaluation on 11 advanced MLLMs, revealing that our benchmark is challenging even for the most sophisticated models.
  arXiv  Detail & Related papers  (2024-08-14T13:23:43Z)
• Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models [62.815222721144636]
  We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5. Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark.
  arXiv  Detail & Related papers  (2024-06-25T05:43:21Z)
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? [99.0305256706604]
  We introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning.
  arXiv  Detail & Related papers  (2024-03-21T17:59:50Z)
• GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers [68.77382332826167]
  Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations.
  arXiv  Detail & Related papers  (2024-02-29T15:26:14Z)
• Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset [33.65525875690291]
  We present the MATH-Vision dataset, a collection of 3,040 high-quality mathematical problems with visual contexts sourced from real math competitions. Through extensive experimentation, we unveil a notable performance gap between current LMMs and human performance on MATH-V. Our detailed categorization allows for a thorough error analysis of LMMs, offering valuable insights to guide future research and development.
  arXiv  Detail & Related papers  (2024-02-22T18:56:38Z)
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts [170.01089233942594]
  MathVista is a benchmark designed to combine challenges from diverse mathematical and visual tasks. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning.
  arXiv  Detail & Related papers  (2023-10-03T17:57:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.