{"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/r-cot-reverse-chain-of-thought-problem","title":"R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models","arxiv_id":"2410.17885","date":"2024-10-23","proceeding":null,"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":"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.","url_abs":"https://arxiv.org/abs/2410.17885v2","url_pdf":"https://arxiv.org/pdf/2410.17885v2.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":"r-cot-reverse-chain-of-thought-problem","repo_url":"https://github.com/dle666/r-cot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"r-cot-reverse-chain-of-thought-problem","repo_url":"https://github.com/yuliang-liu/monkey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.17885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17885"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yuliang-liu/monkey","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dle666/r-cot","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":8,"ran_fixture":1,"ran_violates":1,"unverified":10},"by_repo_kind":{"official":{"samples":21,"ran":11,"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":21,"samples":[{"code_sha256_prefix":"57e95166ade5f25c","entry":"build_transform","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/model_vqa_rcot2b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot2b.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"code_sha256_prefix":"ecc1e50a10f04fa0","entry":"create_one_query","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/build_query.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/build_query.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecc1e50a10f04fa0"}},{"code_sha256_prefix":"93f012e28ba3ca67","entry":"dynamic_preprocess","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/model_vqa_rcot2b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot2b.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93f012e28ba3ca67"}},{"code_sha256_prefix":"6a7cafccc873c34d","entry":"evaluate_code","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/generate_response_geo_qwenvl.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/generate_response_geo_qwenvl.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a7cafccc873c34d"}},{"code_sha256_prefix":"bd77f5f8067f18e9","entry":"find_closest_aspect_ratio","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/model_vqa_rcot2b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot2b.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":"bd77f5f8067f18e9"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/model_vqa_rcot7b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot7b.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":"9ffa907555068ff3","entry":"read_json","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/utilities.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/utilities.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"code_sha256_prefix":"d027e6e473c9fcd4","entry":"refine_caption","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/build_query.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/build_query.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d027e6e473c9fcd4"}},{"code_sha256_prefix":"bfd184123c9012c3","entry":"refine_ocr","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/build_query.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/build_query.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfd184123c9012c3"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/model_vqa_rcot7b.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/model_vqa_rcot7b.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":"d6259b0d9750cac7","entry":"verify_response","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/generate_response_geo_qwenvl.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/generate_response_geo_qwenvl.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}},{"code_sha256_prefix":"6d0fed830d6f1474","entry":"calculate_accuracy","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/geo_acc_calculate.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/geo_acc_calculate.py","link_basis":"first_harvest_node","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":"6d0fed830d6f1474"}},{"code_sha256_prefix":"8b526bb8355d1e07","entry":"conv2text","repo":"dle666/r-cot","repo_kind":"official","path":"R-CoT7B-main/data_mix.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/R-CoT7B-main/data_mix.py","link_basis":"first_harvest_node","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":"8b526bb8355d1e07"}},{"code_sha256_prefix":"c1eaa5bf4d5f383d","entry":"extract_answer","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/extract_answer.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/extract_answer.py","link_basis":"first_harvest_node","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":"c1eaa5bf4d5f383d"}},{"code_sha256_prefix":"ababfc3520297c21","entry":"extract_choice","repo":"dle666/r-cot","repo_kind":"official","path":"GeoQA_test/geo_acc_calculate.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/GeoQA_test/geo_acc_calculate.py","link_basis":"first_harvest_node","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":"ababfc3520297c21"}},{"code_sha256_prefix":"c28eb86a8d14e4ed","entry":"get_most_similar","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/calculate_score.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/calculate_score.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":"c28eb86a8d14e4ed"}},{"code_sha256_prefix":"0da7b678f70430a0","entry":"normalize_extracted_answer","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/calculate_score.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/calculate_score.py","link_basis":"first_harvest_node","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":"0da7b678f70430a0"}},{"code_sha256_prefix":"1694e6d4f46ff13e","entry":"read_csv","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/utilities.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/utilities.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":"1694e6d4f46ff13e"}},{"code_sha256_prefix":"32ae2fb99638aba7","entry":"read_pandas_csv","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/utilities.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/utilities.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":"32ae2fb99638aba7"}},{"code_sha256_prefix":"e7a23ea3695f6437","entry":"safe_equal","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/calculate_score.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/calculate_score.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":"e7a23ea3695f6437"}},{"code_sha256_prefix":"a7852c6582967cfa","entry":"verify_extraction","repo":"dle666/r-cot","repo_kind":"official","path":"MathVista_eval/evaluation/extract_answer.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/extract_answer.py","link_basis":"first_harvest_node","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":"a7852c6582967cfa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}