Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal Models

• URL: http://arxiv.org/abs/2408.13854v2
• Date: Tue, 17 Dec 2024 08:12:25 GMT
• Title: Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal Models
• Authors: Chao Zhang, Jiamin Tang, Jing Xiao,
• Abstract summary: Tangram is a novel benchmark designed to evaluate the performance of LMMs on geometric element recognition. Tangram comprises 1,080 diverse geometric diagrams sourced from primary and secondary school exams, competitions, and textbooks. The top-performing model achieves an accuracy of only 53.0%, highlighting a substantial gap compared to human performance.
• Score: 14.754735603094245
• License:
• Abstract: Significant advancements in Large Multimodal Models (LMMs) have enabled them to tackle complex problems involving visual-mathematical reasoning. However, their ability to identify geometric elements remains underexplored. To address this gap, we introduce Tangram, a novel benchmark designed to evaluate the performance of LMMs on geometric element recognition. Tangram comprises 1,080 diverse geometric diagrams sourced from primary and secondary school exams, competitions, and textbooks, ranging from simple geometric shapes to complex combinations. Each diagram is paired with four questions, resulting in 4,320 visual-question-answer pairs. Unlike existing benchmarks that emphasize higher-level cognition and reasoning, Tangram focuses on understanding geometric elements, requiring models to perform a ``simple yet challenging" counting task. Systematic evaluation of 13 prominent LMMs, such as GPT-4o and Claude 3.5 Sonnet, reveals that these models face significant challenges even in seemingly straightforward tasks. The top-performing model achieves an accuracy of only 53.0%, highlighting a substantial gap compared to human performance. These findings underscore the limitations of current multimodal AI systems in handling basic perception tasks and serve to inspire the development of the next generation of expert-level multimodal foundational models. The data and code will be released soon.

Related papers

• 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)
• 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)
• GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving [40.46491587796371]
  We introduce the GeoEval benchmark, a comprehensive collection that includes a main subset of 2,000 problems, a 750 problems subset focusing on backward reasoning, an augmented subset of 2,000 problems, and a hard subset of 300 problems. Our evaluation of ten LLMs and MMs across these varied subsets reveals that the WizardMath model excels, achieving a 55.67% accuracy rate on the main subset but only a 6.00% accuracy on the hard subset.
  arXiv  Detail & Related papers  (2024-02-15T16:59:41Z)
• G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model [124.68242155098189]
  Large language models (LLMs) have shown remarkable proficiency in human-level reasoning and generation capabilities. G-LLaVA demonstrates exceptional performance in solving geometric problems, significantly outperforming GPT-4-V on the MathVista benchmark with only 7B parameters.
  arXiv  Detail & Related papers  (2023-12-18T17:36:20Z)
• 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)
• MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities [153.37868034779385]
  We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes.
  arXiv  Detail & Related papers  (2023-08-04T17:59:47Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings [63.90855798947425]
  Presentation attacks pose major challenges to most of the biometric modalities. We propose a generalized deep learning-based presentation attack detection network, MVANet. It is inspired by the simplicity and success of hybrid algorithm or fusion of multiple detection networks.
  arXiv  Detail & Related papers  (2020-10-25T22:42:27Z)

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.