{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:37:33Z","timestamp":1743154653383,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794393"},{"type":"electronic","value":"9789819794409"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-9440-9_7","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:06:49Z","timestamp":1730394409000},"page":"81-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mathematical Reasoning via\u00a0Multi-step Self Questioning and\u00a0Answering for\u00a0Small Language Models"],"prefix":"10.1007","author":[{"given":"Kaiyuan","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xuejie","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"7_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR2","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."},{"issue":"240","key":"7_CR3","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: Scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR4","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. CoRR abs\/ arXiv: 2110.14168 (2021)"},{"key":"7_CR5","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized llms. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"7_CR6","unstructured":"Drozdov, A., et al.: Compositional semantic parsing with large language models. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023 (2023)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Dua, D., Gupta, S., Singh, S., Gardner, M.: Successive prompting for decomposing complex questions. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, 7-11 December 2022, pp. 1251\u20131265 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.81"},{"key":"7_CR8","unstructured":"Fu, Y., Peng, H., Ou, L., Sabharwal, A., Khot, T.: Specializing smaller language models towards multi-step reasoning. In: International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 10421\u201310430 (2023)"},{"key":"7_CR9","unstructured":"Fu, Y., Peng, H., Sabharwal, A., Clark, P., Khot, T.: Complexity-based prompting for multi-step reasoning. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1-5 May 2023 (2023)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Ho, N., Schmid, L., Yun, S.: Large language models are reasoning teachers. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, v July 2023. pp. 14852\u201314882 (2023)","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Hsieh, C., et al.: Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In: Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, 9-14 July 2023, pp. 8003\u20138017 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"7_CR12","unstructured":"Khot, T., et al.: Decomposed prompting: A modular approach for solving complex tasks. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1-5 May 2023 (2023)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Li, L.H., Hessel, J., Yu, Y., Ren, X., Chang, K., Choi, Y.: Symbolic chain-of-thought distillation: Small models can also \"think\" step-by-step. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, 9-14 July 2023, pp. 2665\u20132679 (2023)","DOI":"10.18653\/v1\/2023.acl-long.150"},{"key":"7_CR14","unstructured":"Li, S., et al.: Explanations from large language models make small reasoners better. CoRR abs\/ arxiv: 2210.06726 (2022)"},{"key":"7_CR15","unstructured":"Liebel, L., K\u00f6rner, M.: Auxiliary tasks in multi-task learning. CoRR abs\/ arXiv: 1805.06334 (2018)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Magister, L.C., Mallinson, J., Ad\u00e1mek, J., Malmi, E., Severyn, A.: Teaching small language models to reason. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2023, Toronto, Canada, 9-14 July 2023, pp. 1773\u20131781 (2023)","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Miao, S., Liang, C., Su, K.: 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, ACL 2020, Online, 5-10 July 2020. pp. 975\u2013984 (2020)","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"7_CR18","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, NAACL-HLT 2021, Online, 6-11 June 2021, pp. 2080\u20132094 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"7_CR19","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Roy, S., Roth, D.: Solving general arithmetic word problems. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17-21 September 2015, pp. 1743\u20131752 (2015)","DOI":"10.18653\/v1\/D15-1202"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Shridhar, K., Stolfo, A., Sachan, M.: Distilling reasoning capabilities into smaller language models. In: Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, 9-14 July 2023, pp. 7059\u20137073 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"7_CR22","unstructured":"Tay, Y., et\u00a0al.: Ul2: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131 (2022)"},{"key":"7_CR23","unstructured":"Thoppilan, R., et\u00a0al.: Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)"},{"key":"7_CR24","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1-5 May 2023 (2023)"},{"key":"7_CR25","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, 28 November- 9 December 2022 (2022)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Wiegreffe, S., Hessel, J., Swayamdipta, S., Riedl, M.O., Choi, Y.: Reframing human-ai collaboration for generating free-text explanations. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, 10-15 July 2022, pp. 632\u2013658 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.47"},{"key":"7_CR27","unstructured":"Zhou, D., et al.: Least-to-most prompting enables complex reasoning in large language models. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1-5 May 2023 (2023)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9440-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:10:24Z","timestamp":1730394624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9440-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794393","9789819794409"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9440-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}