{"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/training-verifiers-to-solve-math-word","title":"Training Verifiers to Solve Math Word Problems","arxiv_id":"2110.14168","date":"2021-10-27","proceeding":null,"authors":["Karl Cobbe","Vineet Kosaraju","Mohammad Bavarian","Mark Chen","Heewoo Jun","Lukasz Kaiser","Matthias Plappert","Jerry Tworek","Jacob Hilton","Reiichiro Nakano","Christopher Hesse","John Schulman"],"abstract":"State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures of current models and support research, we introduce GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems. We find that even the largest transformer models fail to achieve high test performance, despite the conceptual simplicity of this problem distribution. To increase performance, we propose training verifiers to judge the correctness of model completions. At test time, we generate many candidate solutions and select the one ranked highest by the verifier. We demonstrate that verification significantly improves performance on GSM8K, and we provide strong empirical evidence that verification scales more effectively with increased data than a finetuning baseline.","url_abs":"https://arxiv.org/abs/2110.14168v2","url_pdf":"https://arxiv.org/pdf/2110.14168v2.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":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/openai/grade-school-math","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/facebookresearch/coconut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/lm-sys/routellm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/michelemancusi/LQVAE-separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"training-verifiers-to-solve-math-word","repo_url":"https://github.com/volcengine/verl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"gsm8k","name":"GSM8K","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.14168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14168"}},"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/volcengine/verl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lm-sys/routellm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michelemancusi/LQVAE-separation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/grade-school-math","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/coconut","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/openai/gradeschool-math","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"bd1370d0392aac75","entry":"_get_pool","repo":"volcengine/verl","repo_kind":"listed","path":"verl/utils/reward_score/math_verify.py","file_url":"https://github.com/volcengine/verl/blob/HEAD/verl/utils/reward_score/math_verify.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd1370d0392aac75"}},{"code_sha256_prefix":"19eaf1b935e2aaa4","entry":"_verify_in_subprocess","repo":"volcengine/verl","repo_kind":"listed","path":"verl/utils/reward_score/math_verify.py","file_url":"https://github.com/volcengine/verl/blob/HEAD/verl/utils/reward_score/math_verify.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19eaf1b935e2aaa4"}},{"code_sha256_prefix":"20d6b98a03e76b63","entry":"compute_score","repo":"volcengine/verl","repo_kind":"listed","path":"verl/utils/reward_score/math_verify.py","file_url":"https://github.com/volcengine/verl/blob/HEAD/verl/utils/reward_score/math_verify.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20d6b98a03e76b63"}},{"code_sha256_prefix":"932e8411623db375","entry":"load_jsonl","repo":"kvadityasrivatsa/analyzing-llms-for-mwps","repo_kind":"listed","path":"code/classifier_based_analysis/utils.py","file_url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps/blob/HEAD/code/classifier_based_analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"932e8411623db375"}},{"code_sha256_prefix":"826eabcc26469462","entry":"replace_arguments_with_numbers","repo":"kvadityasrivatsa/analyzing-llms-for-mwps","repo_kind":"listed","path":"code/classifier_based_analysis/utils.py","file_url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps/blob/HEAD/code/classifier_based_analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"826eabcc26469462"}},{"code_sha256_prefix":"642e121e205a94a3","entry":"replace_numbers_with_arguments","repo":"kvadityasrivatsa/analyzing-llms-for-mwps","repo_kind":"listed","path":"code/classifier_based_analysis/utils.py","file_url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps/blob/HEAD/code/classifier_based_analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"642e121e205a94a3"}},{"code_sha256_prefix":"c05515574b2f25c2","entry":"word_length","repo":"kvadityasrivatsa/analyzing-llms-for-mwps","repo_kind":"listed","path":"code/classifier_based_analysis/feature_extraction.py","file_url":"https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps/blob/HEAD/code/classifier_based_analysis/feature_extraction.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c05515574b2f25c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}