mlsanityData to 7 Oct 2026

GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation

arXiv 2406.11503 ↗First posted 17 Jun 2024cs.CV cs.CLcited by 31

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Large language models have seen widespread adoption in math problem-solving. However, in geometry problems that usually require visual aids for better understanding, even the most advanced multi-modal models currently still face challenges in effectively using image information. High-quality data is crucial for enhancing the geometric capabilities of multi-modal models, yet existing open-source datasets and related efforts are either too challenging for direct model learning or suffer from misalignment between text and images. To overcome this issue, we introduce a novel pipeline that leverages GPT-4 and GPT-4V to generate relatively basic geometry problems with aligned text and images, facilitating model learning. We have produced a dataset of 4.9K geometry problems and combined it with 19K open-source data to form our GeoGPT4V dataset. Experimental results demonstrate that the GeoGPT4V dataset significantly improves the geometry performance of various models on the MathVista and MathVision benchmarks. The code is available at https://github.com/Lanyu0303/GeoGPT4V_Project

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 27 of its 43 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

27 of 43 references.

References · 27

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  3. 2023Let's Verify Step by Stepcited by 3,598
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  7. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  8. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  9. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  10. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  11. 2023LIMA: Less Is More for Alignmentcited by 1,080
  12. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
15 more
  1. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  2. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  3. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  4. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  5. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  6. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 516
  7. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  8. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 356
  9. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  10. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 224
  11. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  12. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 155
  13. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  14. 2022UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expressioncited by 137
  15. 2023Automatic Model Selection with Large Language Models for Reasoningcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 17; 2026: 9.

31 papers.

Sort:

By area:

  1. 2025Baichuan-Omni-1.5 Technical Reportcited by 107
  2. 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Modelcited by 64
  3. 2024Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoningcited by 52
  4. 2025MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoningcited by 45
  5. 2024MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Modelcited by 20
  6. 2025M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performancecited by 19
  7. 2025Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integrationcited by 18
  8. 2025Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMscited by 15
  9. 2025DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoningcited by 13
  10. 2024Diagram Formalization Enhanced Multi-Modal Geometry Problem Solvercited by 11
  11. 2025Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skippingcited by 11
  12. 2025GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutionscited by 11
19 more
  1. 2025MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problemscited by 10
  2. 2025Towards Geometry Problem Solving in the Large Model Era: A Surveycited by 8
  3. 2024GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Modelscited by 5
  4. 2025From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphicscited by 5
  5. 2025Generalizable Geometric Image Caption Synthesiscited by 5
  6. 2025Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understandingcited by 4
  7. 2025GeoSDF: Plane Geometry Diagram Synthesis via Signed Distance Fieldcited by 4
  8. 2025A Survey of Deep Learning for Geometry Problem Solvingcited by 4
  9. 2025MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuningcited by 2
  10. 2026Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Trainingcited by 1
  11. 2026GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solvingcited by 1
  12. 2026GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagramscited by 1
  13. 2026GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoningcited by 1
  14. 2024AI's Spatial Intelligence: Evaluating AI's Understanding of Spatial Transformations in PSVT:R and Augmented Realitycited by 0
  15. 2026A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoningcited by 0
  16. 2026BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interactioncited by 0
  17. 2026VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verificationcited by 0
  18. 2026FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generationcited by 0
  19. 2026Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometrycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
  2. 2024Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring
  3. 2024GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
  4. 2024Geo-LLaVA: A Large Multi-Modal Model for Solving Geometry Math Problems with Meta In-Context Learning
  5. 2025GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models
  6. 2025GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language
  7. 2023GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning
  8. 2026GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning