{"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/g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","arxiv_id":"2312.11370","date":"2023-12-18","proceeding":null,"authors":["Jiahui Gao","Renjie Pi","Jipeng Zhang","Jiacheng Ye","Wanjun Zhong","YuFei Wang","Lanqing Hong","Jianhua Han","Hang Xu","Zhenguo Li","Lingpeng Kong"],"abstract":"Large language models (LLMs) have shown remarkable proficiency in human-level reasoning and generation capabilities, which encourages extensive research on their application in mathematical problem solving. However, current work has been largely focused on text-based mathematical problems, with limited investigation in problems involving geometric information. Addressing this gap, we aim to enable LLMs to solve geometric problems by understanding image input. We first analyze the limitations of current Multimodal Large Language Models (MLLMs) in this area: they struggle to accurately comprehending basic geometric elements and their relationships. To overcome these challenges, we take advantage of the unique characteristics of geometric problems (such as unique geometric logical form, and geometric scalability) and the capacity of the textual LLMs to build an enriched multimodal geometry dataset based on existing data. The augmented dataset, Geo170K, contains more than 170K geometric image-caption and question-answer pairs. Utilizing our constructed Geo170K dataset, we develop G-LLaVA, which demonstrates exceptional performance in solving geometric problems, significantly outperforming GPT-4-V on the MathVista benchmark with only 7B parameters.","url_abs":"https://arxiv.org/abs/2312.11370v1","url_pdf":"https://arxiv.org/pdf/2312.11370v1.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":"g-llava-solving-geometric-problem-with-multi","repo_url":"https://github.com/pipilurj/g-llava","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"g-llava-solving-geometric-problem-with-multi","repo_url":"https://github.com/deep-agent/r1-v","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"g-llava-solving-geometric-problem-with-multi","repo_url":"https://github.com/vlm-rl/ocean-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"mathematical-problem-solving","task_name":"Mathematical Problem-Solving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.11370","atlas_url":"https://app.syntology.ai/?focus=2312.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11370"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pipilurj/g-llava","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vlm-rl/ocean-r1","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deep-agent/r1-v","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/eval/model_vqa_llava.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/eval/model_vqa_llava.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/eval/run_llava.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/eval/run_llava.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/eval/model_vqa_llava.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/eval/model_vqa_llava.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"10893c4608c08075","entry":"split_to_even_chunks","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/train/llava_trainer.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/train/llava_trainer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10893c4608c08075"}},{"code_sha256_prefix":"bb35e3ac741bb2c9","entry":"get_mm_adapter_state_maybe_zero_3","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/train/llava_trainer.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/train/llava_trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb35e3ac741bb2c9"}},{"code_sha256_prefix":"735025744c1ab0cf","entry":"maybe_zero_3","repo":"pipilurj/g-llava","repo_kind":"official","path":"gllava/train/llava_trainer.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/train/llava_trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"735025744c1ab0cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}