Go to ACL ARR 2025 July homepageA Survey of Deep Learning for Geometry Problem Solving
Abstract: Geometry problem solving, a crucial aspect of mathematical reasoning, is vital across various domains, including education, the assessment of AI's mathematical abilities, and multimodal capability evaluation.The recent surge in deep learning technologies, particularly the emergence of multimodal large language models, has significantly accelerated research in this area. This paper presents a survey of the applications of deep learning in geometry problem solving, including (i) a comprehensive summary of the relevant tasks in geometry problem solving; (ii) a thorough review of related deep learning methods; (iii) a detailed analysis of evaluation metrics and methods; and (iv) a critical discussion of the current challenges and future directions that can be explored. Our objective is to offer a comprehensive and practical reference of deep learning for geometry problem solving, thereby fostering further advancements in this field. We create a continuously updated list of papers: https://anonymous.4open.science/r/papers-4Km8Pz2Q.
Paper Type: Long
Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond
Research Area Keywords: multimodality, vision question answering, cross-modal application
Contribution Types: Data analysis, Surveys
Languages Studied: English, Chinese
Reassignment Request Area Chair: This is not a resubmission
Reassignment Request Reviewers: This is not a resubmission
A1 Limitations Section: This paper has a limitations section.
A2 Potential Risks: No
A2 Elaboration: This paper is a survey and does not propose new methods, collect new data, or deploy any systems. Therefore, we believe it does not introduce any new ethical, societal, or technical risks.
B Use Or Create Scientific Artifacts: Yes
B1 Cite Creators Of Artifacts: Yes
B1 Elaboration: The datasets included in the survey were cited in Section 2, 3, 4, 5, Appendix A, B and Table 1, 2, 3.
B2 Discuss The License For Artifacts: No
B2 Elaboration: This paper reviews public datasets without directly reusing or redistributing them, so licensing was not discussed. An open-source paper list was released, but no specific license was provided in the paper.
B3 Artifact Use Consistent With Intended Use: No
B3 Elaboration: This survey only includes statistical summaries of public datasets without reuse or redistribution. No external artifacts were used, and our released artifact poses no usage or access concerns.
B4 Data Contains Personally Identifying Info Or Offensive Content: N/A
B4 Elaboration: This work is a survey and does not involve the collection or use of raw data. Dataset analysis was limited to published descriptions and statistics.
B5 Documentation Of Artifacts: No
B5 Elaboration: This work surveys existing datasets without creating new ones; only statistical summaries are provided. The created artifact is a paper list without detailed documentation on domains or demographics.
B6 Statistics For Data: Yes
B6 Elaboration: Relevant statistics of existing datasets are reported in Appendix A, B and Table 1, 2, 3.
C Computational Experiments: Yes
C1 Model Size And Budget: N/A
C1 Elaboration: No models were trained or evaluated, so model size and computational budget do not apply.
C2 Experimental Setup And Hyperparameters: N/A
C2 Elaboration: No model experiments were conducted, so there were no hyperparameters involved.
C3 Descriptive Statistics: Yes
C3 Elaboration: Descriptive statistics are provided in summary tables for existing datasets. See Appendix A, B and Table 1, 2, 3.
C4 Parameters For Packages: N/A
C4 Elaboration: No third-party software packages were used for preprocessing or evaluation.
D Human Subjects Including Annotators: No
D1 Instructions Given To Participants: N/A
D1 Elaboration: No human participants or annotators were involved in this work.
D2 Recruitment And Payment: N/A
D2 Elaboration: No human participants or annotators were involved in this work.
D3 Data Consent: No
D3 Elaboration: No human data was used in this work.
D4 Ethics Review Board Approval: N/A
D4 Elaboration: No ethics approval was required, as this work does not involve human subjects.
D5 Characteristics Of Annotators: N/A
D5 Elaboration: No human annotators were involved in this work.
E Ai Assistants In Research Or Writing: Yes
E1 Information About Use Of Ai Assistants: No
E1 Elaboration: AI assistants were used solely to help with language editing and improving the clarity of the text. No original research content, data analysis, or experimental design was generated by AI.
Author Submission Checklist: yes
Submission Number: 1376
Loading