R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models

• URL: http://arxiv.org/abs/2410.17885v2
• Date: Sun, 27 Oct 2024 09:02:01 GMT
• Title: R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models
• Authors: Linger Deng, Yuliang Liu, Bohan Li, Dongliang Luo, Liang Wu, Chengquan Zhang, Pengyuan Lyu, Ziyang Zhang, Gang Zhang, Errui Ding, Yingying Zhu, Xiang Bai,
• Abstract summary: We propose a two-stage Reverse Chain-of-Thought (R-CoT) geometry problem generation pipeline. First, we introduce GeoChain to produce high-fidelity geometric images and corresponding descriptions. We then design a Reverse A&Q method that reasons step-by-step based on the descriptions and generates questions in reverse from the reasoning results.
• Score: 86.06825304372613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity. To synthesize higher-quality data, we propose a two-stage Reverse Chain-of-Thought (R-CoT) geometry problem generation pipeline. First, we introduce GeoChain to produce high-fidelity geometric images and corresponding descriptions highlighting relations among geometric elements. We then design a Reverse A&Q method that reasons step-by-step based on the descriptions and generates questions in reverse from the reasoning results. Experiments demonstrate that the proposed method brings significant and consistent improvements on multiple LMM baselines, achieving new performance records in the 2B, 7B, and 8B settings. Notably, R-CoT-8B significantly outperforms previous state-of-the-art open-source mathematical models by 16.6% on MathVista and 9.2% on GeoQA, while also surpassing the closed-source model GPT-4o by an average of 13% across both datasets. The code is available at https://github.com/dle666/R-CoT.

Related papers

• TrustGeoGen: Scalable and Formal-Verified Data Engine for Trustworthy Multi-modal Geometric Problem Solving [66.0201510984171]
  We propose a scalable data engine called TrustGeoGen for problem generation. By formal verification, TrustGeoGen produces GeoTrust-200K dataset with guaranteed modality integrity. Experiments reveal the state-of-the-art models achieve only 49.17% accuracy on GeoTrust-test.
  arXiv  Detail & Related papers  (2025-04-22T10:45:23Z)
• DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry [3.859930277034918]
  Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD) We propose DTGBrepGen, a novel topology-geometry decoupled framework for B-rep generation.
  arXiv  Detail & Related papers  (2025-03-17T12:34:14Z)
• GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models [10.443672399225983]
  Vision-parametric models (VLMs) have made significant progress in various multimodal tasks. They still struggle with geometry problems and are significantly limited by their inability to perform mathematical operations not seen during pre-training. We present GeoCoder, which leverages modular code-finetuning to generate and execute code using a predefined geometry function library.
  arXiv  Detail & Related papers  (2024-10-17T12:56:52Z)
• GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation [15.931398242118073]
  GPT-4 and GPT-4V are used to generate basic geometry problems with aligned text and images. We have produced a dataset of 4.9K geometry problems and combined it with 19K open-source data to form our GeoGPT4V dataset. Results demonstrate that the GeoGPT4V dataset significantly improves the geometry performance of various models on the MathVista and MathVision benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T13:04:27Z)
• GOLD: Geometry Problem Solver with Natural Language Description [7.9345421580482185]
  We present the Geometry problem sOlver with natural Language Description (GOLD) model. GOLD enhances the extraction of geometric relations by separately processing symbols and geometric primitives within the diagram. It converts the extracted relations into natural language descriptions, efficiently utilizing large language models to solve geometry math problems.
  arXiv  Detail & Related papers  (2024-05-01T13:00:51Z)
• A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications [67.33002207179923]
  This paper presents a survey of data structures, models, and applications related to geometric GNNs. We provide a unified view of existing models from the geometric message passing perspective. We also summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
  arXiv  Detail & Related papers  (2024-03-01T12:13:04Z)
• 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)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Community Recovery in the Geometric Block Model [38.77098549680883]
  We show that a simple triangle-counting dataset to detect communities in the geometric block model is near-optimal. We also show that our algorithm performs extremely well, both theoretically and practically.
  arXiv  Detail & Related papers  (2022-06-22T18:10:49Z)
• Robust and Accurate Superquadric Recovery: a Probabilistic Approach [29.7543198254021]
  We propose the first probabilistic method to recover superquadrics from point clouds. Our method outperforms the state-of-the-art in terms of accuracy, efficiency, and robustness on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-11-29T13:17:17Z)
• GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning [172.36214872466707]
  We focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams, and theorem knowledge. We propose a Geometric Question Answering dataset GeoQA, containing 5,010 geometric problems with corresponding annotated programs.
  arXiv  Detail & Related papers  (2021-05-30T12:34:17Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)

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.