{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:01:31Z","timestamp":1750309291530,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0116312"],"award-info":[{"award-number":["2022ZD0116312"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679122","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"5405-5409","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Infinity\n            <scp>Math:<\/scp>\n            A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6384-2104","authenticated-orcid":false,"given":"Bo-Wen","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0187-7010","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"China University of Mining &amp; Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9374-2460","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"China University of Mining &amp; Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5259-7094","authenticated-orcid":false,"given":"Guang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Mathqa: Towards interpretable math word problem solving with operation-based formalisms. arXiv preprint arXiv:1905.13319","author":"Amini Aida","year":"2019","unstructured":"Aida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019. Mathqa: Towards interpretable math word problem solving with operation-based formalisms. arXiv preprint arXiv:1905.13319 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29721"},{"key":"e_1_3_2_1_4_1","volume-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588","author":"Chen Wenhu","year":"2022","unstructured":"Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588 (2022)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.489"},{"key":"e_1_3_2_1_6_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","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 preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874","author":"Hendrycks Dan","year":"2021","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 preprint arXiv:2103.03874 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1136"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep Learning for Symbolic Mathematics. arXiv preprint arXiv:1912.01412","author":"Lample Guillaume","year":"2019","unstructured":"Guillaume Lample and Franccois Charton. 2019. Deep Learning for Symbolic Mathematics. arXiv preprint arXiv:1912.01412 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Making large language models better reasoners with step-aware verifier. arXiv preprint arXiv:2206.02336","author":"Li Yifei","year":"2022","unstructured":"Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. 2022. Making large language models better reasoners with step-aware verifier. arXiv preprint arXiv:2206.02336 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems. arXiv preprint arXiv:1705.04146","author":"Ling Wang","year":"2017","unstructured":"Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program induction by rationale generation: Learning to solve and explain algebraic word problems. arXiv preprint arXiv:1705.04146 (2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568","author":"Luo Ziyang","year":"2023","unstructured":"Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2023. Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"A diverse corpus for evaluating and developing English math word problem solvers. arXiv preprint arXiv:2106.15772","author":"Miao Shen-Yun","year":"2021","unstructured":"Shen-Yun Miao, Chao-Chun Liang, and Keh-Yih Su. 2021. A diverse corpus for evaluating and developing English math word problem solvers. arXiv preprint arXiv:2106.15772 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"NumGLUE: A suite of fundamental yet challenging mathematical reasoning tasks. arXiv preprint arXiv:2204.05660","author":"Mishra Swaroop","year":"2022","unstructured":"Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, and Ashwin Kalyan. 2022. NumGLUE: A suite of fundamental yet challenging mathematical reasoning tasks. arXiv preprint arXiv:2204.05660 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Are NLP models really able to solve simple math word problems? arXiv preprint arXiv:2103.07191","author":"Patel Arkil","year":"2021","unstructured":"Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. Are NLP models really able to solve simple math word problems? arXiv preprint arXiv:2103.07191 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_20_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_1_21_1","volume-title":"A 1.8 Million Math Instruction Tuning Dataset. arXiv preprint arXiv:2402.10176","author":"Toshniwal Shubham","year":"2024","unstructured":"Shubham Toshniwal, Ivan Moshkov, Sean Narenthiran, Daria Gitman, Fei Jia, and Igor Gitman. 2024. OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset. arXiv preprint arXiv:2402.10176 (2024)."},{"key":"e_1_3_2_1_22_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824--24837."},{"key":"e_1_3_2_1_25_1","volume-title":"Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284","author":"Yu Longhui","year":"2023","unstructured":"Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. 2023. Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653","author":"Yue Xiang","year":"2023","unstructured":"Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. 2023. Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Agieval: A human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:2304.06364","author":"Zhong Wanjun","year":"2023","unstructured":"Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, and Nan Duan. 2023. Agieval: A human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:2304.06364 (2023)."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Boise ID USA","acronym":"CIKM '24"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679122","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:28Z","timestamp":1750291408000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":27,"alternative-id":["10.1145\/3627673.3679122","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679122","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}