{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:15:01Z","timestamp":1792080901618,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["92470121"],"award-info":[{"award-number":["92470121"]}]},{"name":"National Natural Science Foundation of China","award":["62402016"],"award-info":[{"award-number":["62402016"]}]},{"name":"National Key R&D Program of China","award":["2024YFA1014003"],"award-info":[{"award-number":["2024YFA1014003"]}]},{"name":"Humanities and Social Sciences Research Planning Fund Project of the Ministry of Education","award":["23YJA880091"],"award-info":[{"award-number":["23YJA880091"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3785700","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2770-2781","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Let's Verify Math Questions Step by Step"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8721-0438","authenticated-orcid":false,"given":"Chengyu","family":"Shen","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1757-5322","authenticated-orcid":false,"given":"Zhen Hao","family":"Wong","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1087-8776","authenticated-orcid":false,"given":"Runming","family":"He","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2963-2210","authenticated-orcid":false,"given":"Hao","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3009-2886","authenticated-orcid":false,"given":"Meiyi","family":"Qiang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9501-3369","authenticated-orcid":false,"given":"Zimo","family":"Meng","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6562-1409","authenticated-orcid":false,"given":"Zhengyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0999-6231","authenticated-orcid":false,"given":"Bohan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6283-062X","authenticated-orcid":false,"given":"Zhengzhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1681-4677","authenticated-orcid":false,"given":"Bin","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-5550","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell J. Hewett Mojan Javaheripi Piero Kauffmann James R. Lee Yin Tat Lee Yuanzhi Li Weishung Liu Caio C. T. Mendes Anh Nguyen Eric Price Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Xin Wang Rachel Ward Yue Wu Dingli Yu Cyril Zhang and Yi Zhang. 2024. Phi-4 Technical Report. arXiv:2412.08905 [cs.CL] https:\/\/arxiv.org\/abs\/2412.08905"},{"key":"e_1_3_2_2_2_1","unstructured":"Alon Albalak Duy Phung Nathan Lile Rafael Rafailov Kanishk Gandhi Louis Castricato Anikait Singh Chase Blagden Violet Xiang Dakota Mahan and Nick Haber. 2025. Big-Math: A Large-Scale High-Quality Math Dataset for Reinforcement Learning in Language Models. arXiv:2502.17387 [cs.LG] https:\/\/arxiv.org\/abs\/2502.17387"},{"key":"e_1_3_2_2_3_1","volume-title":"MSC2020 \u2013 Mathematics Subject Classification. https:\/\/mathscinet.ams.org\/mathscinet\/msc\/msc2020","author":"American Mathematical Society","year":"2020","unstructured":"American Mathematical Society, and zbMATH Open. 2020. MSC2020 \u2013 Mathematics Subject Classification. https:\/\/mathscinet.ams.org\/mathscinet\/msc\/msc2020.html. Accessed: 2025-05-08."},{"key":"e_1_3_2_2_4_1","unstructured":"Anthropic. 2024. Claude 3.5 Sonnet Model Card Addendum. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet. Accessed: 2025-05-08."},{"key":"e_1_3_2_2_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML). 454-463","author":"Bansal Kshitij","year":"1904","unstructured":"Kshitij Bansal, Sarah Loos, Markus N. Rabe, Christian Szegedy, and Daniel L. Selsam. 2019. HOList: An Environment for Machine Learning of Higher-Order Logic Theorem Proving. In Proceedings of the 36th International Conference on Machine Learning (ICML). 454-463. https:\/\/arxiv.org\/abs\/1904.03241 Introduces a reinforcement-learning environment for proof search in the HOL Light theorem prover.."},{"key":"e_1_3_2_2_7_1","unstructured":"Akhiad Bercovich Itay Levy Izik Golan Mohammad Dabbah Ran El-Yaniv Omri Puny Ido Galil Zach Moshe Tomer Ronen Najeeb Nabwani et al. 2025. Llama-Nemotron: Efficient Reasoning Models. arXiv:2505.00949 [cs.CL] https:\/\/arxiv.org\/abs\/2505.00949"},{"key":"e_1_3_2_2_8_1","unstructured":"Peter G. Brodeur Thomas A. Buckley Zahir Kanjee Ethan Goh Evelyn Bin Ling Priyank Jain Stephanie Cabral Raja-Elie Abdulnour Adrian Haimovich Jason A. Freed Andrew Olson Daniel J. Morgan Jason Hom Robert Gallo Eric Horvitz Jonathan Chen Arjun K. Manrai and Adam Rodman. 2024. Superhuman performance of a large language model on the reasoning tasks of a physician. arXiv:2412.10849 [cs.AI] https:\/\/arxiv.org\/abs\/2412.10849"},{"key":"e_1_3_2_2_9_1","volume-title":"Mishra","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, and Gaurav et al. Mishra. 2022. PaLM: Scaling Language Modeling with Pathways. arXiv preprint arXiv:2204.02311 (2022). Reports a negative correlation between model size and error rate in code and math problem synthesis tasks.."},{"key":"e_1_3_2_2_10_1","unstructured":"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. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 [cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_2_11_1","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li et al. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2201521119"},{"key":"e_1_3_2_2_13_1","volume-title":"Zhang","author":"Fan Angela","year":"2023","unstructured":"Angela Fan, Beliz Gokkaya, Mark Harman, Mitya Lyubarskiy, Shubho Sengupta, Shin Yoo, and Jie M. Zhang. 2023. Large Language Models for Software Engineering: Survey and Open Problems. arXiv:2310.03533 [cs.SE] https:\/\/arxiv.org\/abs\/2310.03533"},{"key":"e_1_3_2_2_14_1","unstructured":"Chenrui Fan Ming Li Lichao Sun and Tianyi Zhou. 2025. Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill? arXiv:2504.06514 [cs.AI] https:\/\/arxiv.org\/abs\/2504.06514"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-024-02127-3"},{"key":"e_1_3_2_2_17_1","unstructured":"Bofei Gao Feifan Song Zhe Yang Zefan Cai Yibo Miao Qingxiu Dong Lei Li Chenghao Ma Liang Chen Runxin Xu Zhengyang Tang Benyou Wang Daoguang Zan Shanghaoran Quan Ge Zhang Lei Sha Yichang Zhang Xuancheng Ren Tianyu Liu and Baobao Chang. 2024. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models. arXiv:2410.07985 [cs.CL] https:\/\/arxiv.org\/abs\/2410.07985"},{"key":"e_1_3_2_2_18_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. arXiv:2103.03874 [cs.LG] https:\/\/arxiv.org\/abs\/2103.03874"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). 37-52","author":"Honovich Or","year":"2022","unstructured":"Or Honovich, Elad Scaria, Roy Fine, Vivek Srikumar, and Amir Globerson. 2022. Teaching Large Language Models to Self-Instruct. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). 37-52. Compares task-generation quality across model sizes and reports a higher error rate in prompts produced by smaller models.."},{"key":"e_1_3_2_2_20_1","volume-title":"Ming Zhong, Rylan Schaeffer, Siru Ouyang, Jiawei Han, and Sanmi Koyejo.","author":"Jiang Minhao","year":"2024","unstructured":"Minhao Jiang, Ken Ziyu Liu, Ming Zhong, Rylan Schaeffer, Siru Ouyang, Jiawei Han, and Sanmi Koyejo. 2024. Investigating Data Contamination for Pre-training Language Models. arXiv:2401.06059 [cs.CL] https:\/\/arxiv.org\/abs\/2401.06059"},{"key":"e_1_3_2_2_21_1","unstructured":"Jean Kaddour Joshua Harris Maximilian Mozes Herbie Bradley Roberta Raileanu and Robert McHardy. 2023. Challenges and Applications of Large Language Models. arXiv:2307.10169 [cs.CL] https:\/\/arxiv.org\/abs\/2307.10169"},{"key":"e_1_3_2_2_22_1","volume-title":"Austin","author":"Lewkowycz Aitor","year":"2022","unstructured":"Aitor Lewkowycz, David Dohan, Francisco Ruiz, Amber Zeng, Mateusz Lewakowicz, Xinyun Chen, and Jacob et al. Austin. 2022. Solving Quantitative Reasoning Problems with Language Models. arXiv preprint arXiv:2206.14858 (2022)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Belinda Z. Li Been Kim and Zi Wang. 2025. QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks? arXiv:2503.22674 [cs.AI] https:\/\/arxiv.org\/abs\/2503.22674","DOI":"10.52202\/085713-4503"},{"key":"e_1_3_2_2_24_1","volume-title":"Kashif Rasul, Longhui Yu, Albert Jiang, Ziju Shen, Zihan Qin, Bin Dong, Li Zhou, Yann Fleureau, Guillaume Lample, and Stanislas Polu.","author":"Li Jia","year":"2024","unstructured":"Jia Li, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Costa Huang, Kashif Rasul, Longhui Yu, Albert Jiang, Ziju Shen, Zihan Qin, Bin Dong, Li Zhou, Yann Fleureau, Guillaume Lample, and Stanislas Polu. 2024. NuminaMath. https:\/\/github.com\/project-numina\/aimo-progress-prize\/blob\/main\/report\/numina_dataset.pdf. GitHub repository."},{"key":"e_1_3_2_2_25_1","unstructured":"Hao Liang Meiyi Qiang Yuying Li Zefeng He Yongzhen Guo Zhengzhou Zhu Wentao Zhang and Bin Cui. 2025. MathClean: A Benchmark for Synthetic Mathematical Data Cleaning. arXiv:2502.19058 [cs.CL] https:\/\/arxiv.org\/abs\/2502.19058"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.151"},{"key":"e_1_3_2_2_27_1","volume-title":"MathGenie: Generating Synthetic Data with Question Back-Translation for Enhancing Mathematical Reasoning of LLMs. arXiv preprint arXiv:2402.16352","author":"Lu Zimu","year":"2024","unstructured":"Zimu Lu, Aojun Zhou, Houxing Ren, Ke Wang, Weikang Shi, Junting Pan, Mingjie Zhan, and Hongsheng Li. 2024b. MathGenie: Generating Synthetic Data with Question Back-Translation for Enhancing Mathematical Reasoning of LLMs. arXiv preprint arXiv:2402.16352 (2024)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-02046-9"},{"key":"e_1_3_2_2_29_1","unstructured":"Kevin Ma Daniele Grandi Christopher McComb and Kosa Goucher-Lambert. 2024. Exploring the Capabilities of Large Language Models for Generating Diverse Design Solutions. arXiv:2405.02345 [cs.HC] https:\/\/arxiv.org\/abs\/2405.02345"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Mihai Nadas Laura Diosan and Andreea Tomescu. 2025. Synthetic Data Generation Using Large Language Models: Advances in Text and Code. arXiv:2503.14023 [cs.CL] https:\/\/arxiv.org\/abs\/2503.14023","DOI":"10.1109\/ACCESS.2025.3589503"},{"key":"e_1_3_2_2_31_1","unstructured":"Mathematical Association of America. 2025. 2025 American Invitational Mathematics Examination. https:\/\/artofproblemsolving.com\/wiki\/index.php\/2025_AIME_I_Problems. Accessed: 2025-05-01."},{"key":"e_1_3_2_2_32_1","volume-title":"Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, et al.","author":"Jaech Aaron","year":"2024","unstructured":"OpenAI:, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, et al., 2024a. OpenAI o1 System Card. arXiv:2412.16720 [cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_2_2_33_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat Red Avila Igor Babuschkin Suchir Balaji Valerie Balcom Paul Baltescu Haiming Bao Mohammad Bavarian Jeff Belgum Irwan Bello et al. 2024b. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Jialin Ouyang. 2025. TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation. arXiv:2502.13442 [cs.CL] https:\/\/arxiv.org\/abs\/2502.13442","DOI":"10.18653\/v1\/2025.acl-short.84"},{"key":"e_1_3_2_2_35_1","unstructured":"Avinash Patil. 2025. Advancing Reasoning in Large Language Models: Promising Methods and Approaches. arXiv:2502.03671 [cs.CL] https:\/\/arxiv.org\/abs\/2502.03671"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Micha\u0142 Pere\u0142kiewicz and Rafa\u0142 Po\u015bwiata. 2024. A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training. arXiv:2407.07630 [cs.CL] https:\/\/arxiv.org\/abs\/2407.07630","DOI":"10.1007\/978-3-031-81596-6_14"},{"key":"e_1_3_2_2_37_1","volume-title":"Yi R. Fung, Weizhu Chen, Minhao Cheng, and Furu Wei.","author":"Qin Zeyu","year":"2025","unstructured":"Zeyu Qin, Qingxiu Dong, Xingxing Zhang, Li Dong, Xiaolong Huang, Ziyi Yang, Mahmoud Khademi, Dongdong Zhang, Hany Hassan Awadalla, Yi R. Fung, Weizhu Chen, Minhao Cheng, and Furu Wei. 2025. Scaling Laws of Synthetic Data for Language Models. arXiv:2503.19551 [cs.CL] https:\/\/arxiv.org\/abs\/2503.19551"},{"key":"e_1_3_2_2_38_1","unstructured":"Z. Z. Ren Zhihong Shao Junxiao Song Huajian Xin Haocheng Wang Wanjia Zhao Liyue Zhang Zhe Fu Qihao Zhu Dejian Yang Z. F. Wu Zhibin Gou Shirong Ma Hongxuan Tang Yuxuan Liu Wenjun Gao Daya Guo and Chong Ruan. 2025. DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition. arXiv:2504.21801 [cs.CL] https:\/\/arxiv.org\/abs\/2504.21801"},{"key":"e_1_3_2_2_39_1","volume-title":"Analysing Mathematical Reasoning Abilities of Neural Models. arXiv preprint arXiv:1904.01557","author":"Saxton David","year":"2019","unstructured":"David Saxton, Edward Grefenstette, Felix Hill, and Pushmeet Kohli. 2019. Analysing Mathematical Reasoning Abilities of Neural Models. arXiv preprint arXiv:1904.01557 (2019)."},{"key":"e_1_3_2_2_40_1","volume-title":"Let's Verify Math Questions Step by Step. arXiv preprint arXiv:2505.13903","author":"Shen Chengyu","year":"2025","unstructured":"Chengyu Shen, Zhen\u00a0Hao Wong, Runming He, Hao Liang, Meiyi Qiang, Zimo Meng, Zhengyang Zhao, Bohan Zeng, Zhengzhou Zhu, Bin Cui, and Wentao Zhang. 2025. Let's Verify Math Questions Step by Step. arXiv preprint arXiv:2505.13903 (2025)."},{"key":"e_1_3_2_2_41_1","volume-title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models. arXiv preprint arXiv:2501.03124","author":"Song Mingyang","year":"2025","unstructured":"Mingyang Song, Zhaochen Su, Xiaoye Qu, Jiawei Zhou, and Yu Cheng. 2025. PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models. arXiv preprint arXiv:2501.03124 (2025)."},{"key":"e_1_3_2_2_42_1","volume-title":"Mm-verify: Enhancing multimodal reasoning with chain-of-thought verification. arXiv preprint arXiv:2502.13383","author":"Sun Linzhuang","year":"2025","unstructured":"Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Tianpeng Li, Fan Yang, Zenan Zhou, and Wentao Zhang. 2025. Mm-verify: Enhancing multimodal reasoning with chain-of-thought verification. arXiv preprint arXiv:2502.13383 (2025)."},{"key":"e_1_3_2_2_43_1","volume-title":"Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazaridou, Orhan Firat, James Molloy, Michael Isard, et al., 2024. Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_2_2_44_1","volume-title":"Do Large Language Model Benchmarks Test Reliability? arXiv preprint arXiv:2502.03461","author":"Vendrow Joshua","year":"2025","unstructured":"Joshua Vendrow, Edward Vendrow, Sara Beery, and Aleksander M\u0105dry. 2025. Do Large Language Model Benchmarks Test Reliability? arXiv preprint arXiv:2502.03461 (2025)."},{"key":"e_1_3_2_2_45_1","unstructured":"Pablo Villalobos Anson Ho Jaime Sevilla Tamay Besiroglu Lennart Heim and Marius Hobbhahn. 2024. Will we run out of data? Limits of LLM scaling based on human-generated data. arXiv:2211.04325 [cs.LG] https:\/\/arxiv.org\/abs\/2211.04325"},{"key":"e_1_3_2_2_46_1","volume-title":"Math-Shepherd: A Label-Free Step-by-Step Verifier for LLMs in Mathematical Reasoning. arXiv preprint arXiv:2312.08935","author":"Wang Peiyi","year":"2023","unstructured":"Peiyi Wang, Lei Li, Zhihong Shao, Renxiang Xu, Damai Dai, Yifei Li, Deli Chen, Yang Wu, and Zhifang Sui. 2023. Math-Shepherd: A Label-Free Step-by-Step Verifier for LLMs in Mathematical Reasoning. arXiv preprint arXiv:2312.08935 (2023)."},{"key":"e_1_3_2_2_47_1","unstructured":"Jason Wei Maarten Du Xuezhi Wang Shawn Ren and et al. 2022. Emergent Abilities of Large Language Models. arXiv preprint arXiv:2206.07682 (2022). Shows that larger models not only answer questions more accurately but also generate fewer invalid or nonsensical outputs.."},{"key":"e_1_3_2_2_48_1","volume-title":"Chi, Quoc Le, and Denny Zhou","author":"Wei Jason","year":"2023","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:2201.11903 [cs.CL] https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_2_2_49_1","unstructured":"Yifan Xu Xiao Liu Xinghan Liu Zhenyu Hou Yueyan Li Xiaohan Zhang Zihan Wang Aohan Zeng Zhengxiao Du Wenyi Zhao Jie Tang and Yuxiao Dong. 2024. ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline. arXiv:2404.02893 [cs.CL] https:\/\/arxiv.org\/abs\/2404.02893"},{"key":"e_1_3_2_2_50_1","unstructured":"An Yang Beichen Zhang Binyuan Hui Bofei Gao Bowen Yu Chengpeng Li Dayiheng Liu Jianhong Tu Jingren Zhou Junyang Lin Keming Lu Mingfeng Xue Runji Lin Tianyu Liu Xingzhang Ren and Zhenru Zhang. 2024. Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement. arXiv:2409.12122 [cs.CL] https:\/\/arxiv.org\/abs\/2409.12122"},{"key":"e_1_3_2_2_51_1","unstructured":"Sen Yang Yafu Li Wai Lam and Yu Cheng. 2025. Multi-LLM Collaborative Search for Complex Problem Solving. arXiv:2502.18873 [cs.AI] https:\/\/arxiv.org\/abs\/2502.18873"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.524"},{"key":"e_1_3_2_2_53_1","unstructured":"Jiayi Zhao Cunjun Zhang Chengyu Wang Yongzhi Cao and Jianye Hao. 2023. AlphaGeometry: Interactive Theorem Proving in Geometry with Deep Learning. In Proceedings of the 11th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=dsvm0BxkFH Combines neural guidance with reinforcement learning to automate Euclidean-geometry proof construction.."},{"key":"e_1_3_2_2_54_1","volume-title":"Processbench: Identifying process errors in mathematical reasoning. arXiv preprint arXiv:2412.06559","author":"Zheng Chujie","year":"2024","unstructured":"Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2024. Processbench: Identifying process errors in mathematical reasoning. arXiv preprint arXiv:2412.06559 (2024)."},{"key":"e_1_3_2_2_55_1","volume-title":"Jing Sha, Zhichao Sheng, Shijin Wang, and Ji-Rong Wen.","author":"Zhou Kun","year":"2024","unstructured":"Kun Zhou, Beichen Zhang, Jiapeng Wang, Zhipeng Chen, Wayne Xin Zhao, Jing Sha, Zhichao Sheng, Shijin Wang, and Ji-Rong Wen. 2024. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models. arXiv:2405.14365 [cs.CL] https:\/\/arxiv.org\/abs\/2405.14365"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:02:23Z","timestamp":1787688143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3785700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":55,"alternative-id":["10.1145\/3770854.3785700","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3785700","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}