{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gold-geometry-problem-solver-with-natural","title":"GOLD: Geometry Problem Solver with Natural Language Description","arxiv_id":"2405.00494","date":"2024-05-01","proceeding":null,"authors":["Jiaxin Zhang","Yashar Moshfeghi"],"abstract":"Addressing the challenge of automated geometry math problem-solving in artificial intelligence (AI) involves understanding multi-modal information and mathematics. Current methods struggle with accurately interpreting geometry diagrams, which hinders effective problem-solving. To tackle this issue, 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. Subsequently, it converts the extracted relations into natural language descriptions, efficiently utilizing large language models to solve geometry math problems. Experiments show that the GOLD model outperforms the Geoformer model, the previous best method on the UniGeo dataset, by achieving accuracy improvements of 12.7% and 42.1% in calculation and proving subsets. Additionally, it surpasses the former best model on the PGPS9K and Geometry3K datasets, PGPSNet, by obtaining accuracy enhancements of 1.8% and 3.2%, respectively.","url_abs":"https://arxiv.org/abs/2405.00494v1","url_pdf":"https://arxiv.org/pdf/2405.00494v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gold-geometry-problem-solver-with-natural","repo_url":"https://github.com/neurasearch/geometry-diagram-description","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-question-answering","task_name":"Mathematical Question Answering"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/mathematical-question-answering-on-geometry3k","task":"Mathematical Question Answering","dataset":"Geometry3K","model":"GOLD","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy (%)":"69.1"},"uses_additional_data":false},{"leaderboard":"/sota/mathematical-reasoning-on-geoqa","task":"Mathematical Reasoning","dataset":"GeoQA","model":"GOLD","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy (%)":"75.2"},"uses_additional_data":false},{"leaderboard":"/sota/mathematical-reasoning-on-pgps9k","task":"Mathematical Reasoning","dataset":"PGPS9K","model":"GOLD","rank_in_archive_order":1,"of":6,"metrics":{"Completion accuracy":"65.8"},"uses_additional_data":false},{"leaderboard":"/sota/mathematical-reasoning-on-unigeo","task":"Mathematical Reasoning","dataset":"UniGeo","model":"GOLD","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"98.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.00494","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}