{"work":{"id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","openalex_id":null,"doi":"10.1002/j.1545-","arxiv_id":"2110.14168","raw_key":null,"title":"Training Verifiers to Solve Math Word Problems","authors":null,"authors_text":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman","year":2021,"venue":"cs.LG","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.","external_url":"https://arxiv.org/abs/2110.14168","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-11T03:27:47.058704+00:00","pith_arxiv_id":"2110.14168","created_at":"2026-05-09T03:55:08.450539+00:00","updated_at":"2026-07-11T11:50:26.030339+00:00","title_quality_ok":true,"display_title":"Training Verifiers to Solve Math Word Problems","render_title":"Training Verifiers to Solve Math Word Problems"},"hub":{"state":{"work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","tier":"mega_hub","tier_reason":"1,000+ Pith inbound or 100,000+ external citations","pith_inbound_count":1496,"external_cited_by_count":null,"distinct_field_count":34,"first_pith_cited_at":"2021-12-01T22:24:34+00:00","last_pith_cited_at":"2026-07-09T17:35:02+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"needed","recognition_status":"needed","updated_at":"2026-08-21T07:19:27.201994+00:00","tier_text":"mega_hub"},"tier":"mega_hub","role_counts":[{"context_role":"background","n":126},{"context_role":"dataset","n":101},{"context_role":"method","n":7},{"context_role":"baseline","n":4},{"context_role":"other","n":2}],"polarity_counts":[{"context_polarity":"background","n":114},{"context_polarity":"use_dataset","n":99},{"context_polarity":"unclear","n":16},{"context_polarity":"use_method","n":7},{"context_polarity":"baseline","n":4}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Training Verifiers to Solve Math Word Problems","claims":[{"claim_text":"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 ge","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Training Verifiers to Solve Math Word Problems because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T18:03:31.006350+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"07c47add-2301-4164-9d06-23347fc20617","orcid":null,"display_name":"Karl Cobbe"},{"id":"edf3b705-ff6d-4713-9b26-27729234c00d","orcid":null,"display_name":"Vineet Kosaraju"},{"id":"9253b15a-b5df-4d8c-bad6-79bec0dcd54d","orcid":null,"display_name":"Mohammad Bavarian"},{"id":"27b716ab-b5bb-4619-9617-be39d50e5f88","orcid":null,"display_name":"Mark Chen"},{"id":"dfca2058-03d1-4251-92fe-0eaddf1dfcf0","orcid":null,"display_name":"Heewoo Jun"},{"id":"7b67bce8-4222-4c96-93ed-a2ccbbe6513d","orcid":null,"display_name":"Lukasz Kaiser"}]},"error":null,"updated_at":"2026-05-13T17:24:05.834629+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T17:53:40.535835+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":139},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":115},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":113},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":107},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":104},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":78},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":77},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":77},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":70},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":65},{"title":"Measuring Massive Multitask Language Understanding","work_id":"e87ec49a-544b-4ec8-8991-75298c64ff5e","shared_citers":61},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":57},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":54},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":48},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":48},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":47},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":40},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":38},{"title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","work_id":"513eb205-04ca-4722-9a43-a74e8cbe7e85","shared_citers":35},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":35},{"title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","work_id":"a8d50b24-bdf5-46ed-bc4f-2927dfd81f1d","shared_citers":35},{"title":"Instruction-Following Evaluation for Large Language Models","work_id":"3aa06177-125a-4f5a-8f4a-8070c5986c26","shared_citers":33},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":33},{"title":"Let's Verify Step by Step","work_id":"6d05b790-04c5-4fd2-91b2-ba1dfdd5770f","shared_citers":32}],"time_series":[{"n":1,"year":2021},{"n":6,"year":2022},{"n":16,"year":2023},{"n":30,"year":2024},{"n":16,"year":2025},{"n":401,"year":2026}]},"error":null,"updated_at":"2026-05-13T17:25:55.152933+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T17:53:39.755816+00:00"},"reader_index":{"job_type":"reader_index","status":"succeeded","result":{"note":"annotated reader requires full-text/OA fetch; shell is wired for mega hubs","status":"reader queued"},"error":null,"updated_at":"2026-06-29T00:28:12.424078+00:00"},"recognition_alignment":{"job_type":"recognition_alignment","status":"succeeded","result":{"modules":["IndisputableMonolith.Sport.PeakPerformanceFromJCost","IndisputableMonolith.Sports.PeakPerformanceFromPhiLadder","IndisputableMonolith.Cognition.AnimalZComplexityBound","IndisputableMonolith.Information.ChurchTuring","IndisputableMonolith.Education.MasteryThresholdFromGap45","IndisputableMonolith.Flight.Falsifiers","IndisputableMonolith.Materials.RoomTSuperconductorCandidate","IndisputableMonolith.MusicTheory.Rhythm"],"query_chars":938},"error":null,"updated_at":"2026-06-29T00:28:34.193407+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Training Verifiers to Solve Math Word Problems","claims":[{"claim_text":"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 ge","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Training Verifiers to Solve Math Word Problems because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T18:03:31.004378+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Training Verifiers to Solve Math Word Problems","claims":[{"claim_text":"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 ge","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Training Verifiers to Solve Math Word Problems because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T17:25:52.713246+00:00"}},"summary":{"title":"Training Verifiers to Solve Math Word Problems","claims":[{"claim_text":"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 ge","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Training Verifiers to Solve Math Word Problems because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":139},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":115},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":113},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":107},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":104},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":78},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":77},{"title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","shared_citers":77},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":70},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":65},{"title":"Measuring Massive Multitask Language Understanding","work_id":"e87ec49a-544b-4ec8-8991-75298c64ff5e","shared_citers":61},{"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","shared_citers":57},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":54},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":48},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":48},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":47},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":40},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":38},{"title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","work_id":"513eb205-04ca-4722-9a43-a74e8cbe7e85","shared_citers":35},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":35},{"title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","work_id":"a8d50b24-bdf5-46ed-bc4f-2927dfd81f1d","shared_citers":35},{"title":"Instruction-Following Evaluation for Large Language Models","work_id":"3aa06177-125a-4f5a-8f4a-8070c5986c26","shared_citers":33},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":33},{"title":"Let's Verify Step by Step","work_id":"6d05b790-04c5-4fd2-91b2-ba1dfdd5770f","shared_citers":32}],"time_series":[{"n":1,"year":2021},{"n":6,"year":2022},{"n":16,"year":2023},{"n":30,"year":2024},{"n":16,"year":2025},{"n":401,"year":2026}]},"authors":[{"id":"dfca2058-03d1-4251-92fe-0eaddf1dfcf0","orcid":null,"display_name":"Heewoo Jun","source":"manual","import_confidence":0.72},{"id":"07c47add-2301-4164-9d06-23347fc20617","orcid":null,"display_name":"Karl Cobbe","source":"manual","import_confidence":0.72},{"id":"7b67bce8-4222-4c96-93ed-a2ccbbe6513d","orcid":null,"display_name":"Lukasz Kaiser","source":"manual","import_confidence":0.72},{"id":"27b716ab-b5bb-4619-9617-be39d50e5f88","orcid":null,"display_name":"Mark Chen","source":"manual","import_confidence":0.72},{"id":"9253b15a-b5df-4d8c-bad6-79bec0dcd54d","orcid":null,"display_name":"Mohammad Bavarian","source":"manual","import_confidence":0.72},{"id":"edf3b705-ff6d-4713-9b26-27729234c00d","orcid":null,"display_name":"Vineet Kosaraju","source":"manual","import_confidence":0.72}]}}