{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:27:09Z","timestamp":1763922429765,"version":"3.45.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093677","type":"print"},{"value":"9783032093684","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09368-4_23","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:05Z","timestamp":1763921645000},"page":"378-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Long Math Reasoning Problem Generation"],"prefix":"10.1007","author":[{"given":"Changwei","family":"Li","sequence":"first","affiliation":[]},{"given":"Guangping","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zihao","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Amini, A., Gabriel, S., Lin, S., Koncel-Kedziorski, R., Choi, Y., Hajishirzi, H.: Mathqa: Towards interpretable math word problem solving with operation-based formalisms. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 2357\u20132367 (2019)","DOI":"10.18653\/v1\/N19-1245"},{"key":"23_CR2","unstructured":"An, C., et al.: L-eval: Instituting standardized evaluation for long context language models. arXiv preprint arXiv:2307.11088 (2023)"},{"key":"23_CR3","unstructured":"Bai, Y., et\u00a0al.: Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508 (2023)"},{"issue":"2","key":"23_CR4","first-page":"12","volume":"13","author":"J Boaler","year":"1993","unstructured":"Boaler, J.: The role of contexts in the mathematics classroom: do they make mathematics more \u201creal\u2019\u2019? For Learn. Math. 13(2), 12\u201317 (1993)","journal-title":"For Learn. Math."},{"key":"23_CR5","unstructured":"Bobrow, D., et\u00a0al.: Natural language input for a computer problem solving system (1964)"},{"key":"23_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR7","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"23_CR8","unstructured":"Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., Gardner, M.: Drop: a reading comprehension benchmark requiring discrete reasoning over paragraphs. arXiv preprint arXiv:1903.00161 (2019)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Guha, N., et\u00a0al.: Legalbench: A collaboratively built benchmark for measuring legal reasoning in large language models. Adv. Neural Inform. Process. Syst. 36 (2024)","DOI":"10.2139\/ssrn.4583531"},{"key":"23_CR10","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874 (2021)"},{"key":"23_CR11","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"23_CR12","volume-title":"Thinking, Fast and Slow","author":"D Kahneman","year":"2011","unstructured":"Kahneman, D.: Thinking, Fast and Slow. Farrar, Straus and Giroux (2011)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, M., Zheng, Z., Zhang, M.: Loogle: Can long-context language models understand long contexts? arXiv preprint arXiv:2311.04939 (2023)","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Ling, W., Yogatama, D., Dyer, C., Blunsom, P.: Program induction by rationale generation: Learning to solve and explain algebraic word problems. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 158\u2013167 (2017)","DOI":"10.18653\/v1\/P17-1015"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Inter-gps: Interpretable geometry problem solving with formal language and symbolic reasoning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6774\u20136786 (2021)","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Miao, S.Y., Liang, C.C., Su, K.Y.: A diverse corpus for evaluating and developing English math word problem solvers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 975\u2013984 (2020)","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"23_CR17","unstructured":"OpenAI, R.: Gpt-4 technical report. arxiv 2303.08774. View in Article 2(5) (2023)"},{"key":"23_CR18","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Patel, A., Bhattamishra, S., Goyal, N.: Are NLP models really able to solve simple math word problems? In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2080\u20132094 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Shaham, U., et\u00a0al.: Scrolls: Standardized comparison over long language sequences. In: Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.823"},{"key":"23_CR21","unstructured":"Tay, Y., et al.: Long range arena: A benchmark for efficient transformers. arXiv preprint arXiv:2011.04006 (2020)"},{"key":"23_CR22","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, X., Shi, S.: Deep neural solver for math word problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 845\u2013854 (2017)","DOI":"10.18653\/v1\/D17-1088"},{"key":"23_CR24","unstructured":"Xu, X., Xiao, T., Chao, Z., Huang, Z., Yang, C., Wang, Y.: Can LLMs solve longer math word problems better? arXiv preprint arXiv:2405.14804 (2024). https:\/\/arxiv.org\/abs\/2405.14804"},{"key":"23_CR25","unstructured":"Zhao, W., Shang, M., Liu, Y., Wang, L., Liu, J.: Ape210k: A large-scale and template-rich dataset of math word problems. arXiv preprint arXiv:2009.11506 (2020)"},{"key":"23_CR26","unstructured":"Zhou, Z., et al.: Is your model really a good math reasoner? evaluating mathematical reasoning with checklist. In: Proceedings of the International Conference on Learning Representations (ICLR) (2025)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Learning by analogy: diverse questions generation in math word problem. In: Findings of the Association for Computational Linguistics: ACL, pp. 11091\u201311104 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.705"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Mathattack: attacking large language models towards math solving ability. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 19750\u201319758 (2024)","DOI":"10.1609\/aaai.v38i17.29949"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09368-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:14:10Z","timestamp":1763921650000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09368-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032093677","9783032093684"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09368-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}