{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:28:22Z","timestamp":1783096102726,"version":"3.54.6"},"reference-count":120,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"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":["Evol. Intel."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s12065-024-00957-0","type":"journal-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T11:01:50Z","timestamp":1720436510000},"page":"3113-3150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards robust automated math problem solving: a survey of statistical and deep learning approaches"],"prefix":"10.1007","volume":"17","author":[{"given":"Amrutesh","family":"Saraf","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooja","family":"Kamat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilpa","family":"Gite","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satish","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ketan","family":"Kotecha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,8]]},"reference":[{"key":"957_CR1","doi-asserted-by":"crossref","unstructured":"Wang A, Singh A, Michael J, Hill F, Levy O, Bowman SR (2018) Glue: a multi-task benchmark and analysis platform for natural language understanding. In: BlackboxNLPEMNLP","DOI":"10.18653\/v1\/W18-5446"},{"key":"957_CR2","unstructured":"Wang A, Pruksachatkun Y, Nangia N, Singh A, Michael J, Hill F, Levy O, Bowman, S (2019) Superglue: a stickier benchmark for general-purpose language understanding systems. In: Wallach H, Larochelle H, Beygelzimer A, Alch\u00e9-Buc F, Fox E, Garnett R (eds) Advances in neural information processing systems, vol 32. Curran Associates, Inc., Red Hook https:\/\/proceedings.neurips.cc\/paper%5Ffiles\/paper\/2019\/file\/4496bf24afe7fab6f046bf4923da8de6-Paper.pdf"},{"key":"957_CR3","doi-asserted-by":"publisher","unstructured":"Mishra S, Mitra A, Varshney N, Sachdeva B, Clark P, Baral C, Kalyan A (2022) NumGLUE: a suite of fundamental yet challenging mathematical reasoning tasks. In: Muresan S, Nakov P, Villavicencio A (eds) Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: Long Papers), pp 3505\u20133523. Association for Computational Linguistics, Dublin, Ireland. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.246","DOI":"10.18653\/v1\/2022.acl-long.246"},{"key":"957_CR4","unstructured":"Bobrow DG (1960) A question-answering system for high school algebra word problems. In: AFIPS \u201964 (Fall, Part I)"},{"issue":"2","key":"957_CR5","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10462-009-9110-0","volume":"29","author":"A Mukherjee","year":"2008","unstructured":"Mukherjee A, Garain U (2008) A review of methods for automatic understanding of natural language mathematical problems. Artif Intell Rev 29(2):93\u2013122. https:\/\/doi.org\/10.1007\/s10462-009-9110-0","journal-title":"Artif Intell Rev"},{"key":"957_CR6","doi-asserted-by":"publisher","unstructured":"Thawani A, Pujara J, Ilievski F, Szekely P (2021) Representing numbers in NLP: a survey and a vision. In: Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 644\u2013656. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.53","DOI":"10.18653\/v1\/2021.naacl-main.53"},{"key":"957_CR7","unstructured":"Sundaram SS, Gurajada S, Fisichella MPD, Abraham SS (2022) Why are NLP models fumbling at elementary math? A survey of deep learning based word problem solvers. arXiv:abs\/2205.15683 (2022)"},{"key":"957_CR8","unstructured":"Faldu K, Sheth A, Kikani P, Gaur M, Avasthi A (2021) Towards tractable mathematical reasoning: Challenges, strategies, and opportunities for solving math word problems. arXiv:abs\/2111.05364 (2021)"},{"key":"957_CR9","doi-asserted-by":"publisher","unstructured":"Lu P, Qiu L, Yu W, Welleck S, Chang K-W (2023) A survey of deep learning for mathematical reasoning. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers), pp 14605\u201314631. Association for Computational Linguistics, Toronto, Canada. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.817","DOI":"10.18653\/v1\/2023.acl-long.817"},{"issue":"5","key":"957_CR10","doi-asserted-by":"publisher","first-page":"565","DOI":"10.3758\/BF03207654","volume":"17","author":"CR Fletcher","year":"1985","unstructured":"Fletcher CR (1985) Understanding and solving arithmetic word problems: a computer simulation. Behav Res Methods Instrum Comput 17(5):565\u2013571","journal-title":"Behav Res Methods Instrum Comput"},{"issue":"3","key":"957_CR11","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1207\/s1532690xci0103_1","volume":"1","author":"DJ Briars","year":"1984","unstructured":"Briars DJ, Larkin JH (1984) An integrated model of skill in solving elementary word problems. Cogn Instr 1(3):245\u2013296","journal-title":"Cogn Instr"},{"issue":"2","key":"957_CR12","doi-asserted-by":"publisher","first-page":"147","DOI":"10.3758\/BF03201014","volume":"18","author":"D Dellarosa","year":"1986","unstructured":"Dellarosa D (1986) A computer simulation of children\u2019s arithmetic word-problem solving. Behav Res Methods Instrum Comput 18(2):147\u2013154","journal-title":"Behav Res Methods Instrum Comput"},{"key":"957_CR13","doi-asserted-by":"publisher","unstructured":"Kushman N, Artzi Y, Zettlemoyer L, Barzilay R (2014) Learning to automatically solve algebra word problems. In: Toutanova K, Wu H (eds) Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 1: Long Papers), pp 271\u2013281. Association for Computational Linguistics, Baltimore, Maryland. https:\/\/doi.org\/10.3115\/v1\/P14-1026","DOI":"10.3115\/v1\/P14-1026"},{"key":"957_CR14","doi-asserted-by":"publisher","unstructured":"Hosseini MJ, Hajishirzi H, Etzioni O, Kushman N (2014) Learning to solve arithmetic word problems with verb categorization. In: Moschitti A, Pang B, Daelemans W (eds) Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 523\u2013533. Association for computational linguistics, Doha, Qatar. https:\/\/doi.org\/10.3115\/v1\/D14-1058","DOI":"10.3115\/v1\/D14-1058"},{"key":"957_CR15","doi-asserted-by":"publisher","unstructured":"Zhou L, Dai S, Chen L (2015) Learn to solve algebra word problems using quadratic programming. In: M\u00e0rquez L, Callison-Burch C, Su J (eds) Proceedings of the 2015 conference on empirical methods in natural language processing, pp 817\u2013822. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/D15-1096","DOI":"10.18653\/v1\/D15-1096"},{"key":"957_CR16","doi-asserted-by":"crossref","unstructured":"Upadhyay S, Chang M-W (2017) Annotating derivations: a new evaluation strategy and dataset for algebra word problems. In: Lapata M, Blunsom P, Koller A (eds) Proceedings of the 15th conference of the European chapter of the association for computational linguistics: volume 1, Long Papers, pp 494\u2013504. Association for Computational Linguistics, Valencia, Spain. https:\/\/aclanthology.org\/E17-1047","DOI":"10.18653\/v1\/E17-1047"},{"key":"957_CR17","doi-asserted-by":"publisher","unstructured":"Huang D, Shi S, Lin C-Y, Yin J, Ma W-Y (2016) How well do computers solve math word problems? large-scale dataset construction and evaluation. In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers), pp 887\u2013896. Association for Computational Linguistics, Berlin, Germany. https:\/\/doi.org\/10.18653\/v1\/P16-1084","DOI":"10.18653\/v1\/P16-1084"},{"key":"957_CR18","doi-asserted-by":"publisher","unstructured":"Huang D, Shi S, Lin C-Y, Yin J (2017) Learning fine-grained expressions to solve math word problems. In: Palmer M, Hwa R, Riedel S (eds) Proceedings of the 2017 conference on empirical methods in natural language processing, pp 805\u2013814. Association for Computational Linguistics, Copenhagen, Denmark. https:\/\/doi.org\/10.18653\/v1\/D17-1084. https:\/\/aclanthology.org\/D17-1084","DOI":"10.18653\/v1\/D17-1084"},{"key":"957_CR19","doi-asserted-by":"publisher","unstructured":"Roy S, Roth D (2017) Unit dependency graph and its application to arithmetic word problem solving. Proceedings of the AAAI conference on artificial intelligence vol 31, no. 1. https:\/\/doi.org\/10.1609\/aaai.v31i1.10959","DOI":"10.1609\/aaai.v31i1.10959"},{"key":"957_CR20","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger KQ (eds) Advances in neural information processing systems, vol 27. Curran Associates, Inc., Red Hook, NY. https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/a14ac55a4f27472c5d894ec1c3c743d2-Paper.pdf"},{"issue":"8","key":"957_CR21","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"957_CR22","doi-asserted-by":"publisher","unstructured":"Cho K, Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1724\u20131734. Association for Computational Linguistics, Doha, Qatar. https:\/\/doi.org\/10.3115\/v1\/D14-1179","DOI":"10.3115\/v1\/D14-1179"},{"key":"957_CR23","doi-asserted-by":"publisher","unstructured":"Wang Y, Liu X, Shi S (2017) Deep neural solver for math word problems. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 845\u2013854. Association for Computational Linguistics, Copenhagen, Denmark. https:\/\/doi.org\/10.18653\/v1\/D17-1088","DOI":"10.18653\/v1\/D17-1088"},{"key":"957_CR24","doi-asserted-by":"publisher","unstructured":"Ling W, Yogatama D, Dyer C, Blunsom P (2017) 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. Association for Computational Linguistics, Vancouver, Canada. https:\/\/doi.org\/10.18653\/v1\/P17-1015","DOI":"10.18653\/v1\/P17-1015"},{"key":"957_CR25","doi-asserted-by":"publisher","unstructured":"Amini A, Gabriel S, Lin S, Koncel-Kedziorski R, Choi Y, Hajishirzi H (2019) Math QA: 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. Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/doi.org\/10.18653\/v1\/N19-1245","DOI":"10.18653\/v1\/N19-1245"},{"key":"957_CR26","doi-asserted-by":"publisher","unstructured":"Chiang T-R, Chen Y-N (2019) Semantically-aligned equation generation for solving and reasoning math word problems. 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 2656\u20132668. Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/doi.org\/10.18653\/v1\/N19-1272","DOI":"10.18653\/v1\/N19-1272"},{"key":"957_CR27","doi-asserted-by":"publisher","unstructured":"Qin J, Lin L, Liang X, Zhang R, Lin L (2020) Semantically-aligned universal tree-structured solver for math word problems. In: Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pp 3780\u20133789. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.309 . https:\/\/aclanthology.org\/2020.emnlp-main.309","DOI":"10.18653\/v1\/2020.emnlp-main.309"},{"key":"957_CR28","doi-asserted-by":"publisher","unstructured":"Qin J, Liang X, Hong Y, Tang J, Lin L (2021) Neural-symbolic solver for math word problems with auxiliary tasks. In: Zong C, Xia F, Li W, Navigli R (eds) 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 5870\u20135881. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.456","DOI":"10.18653\/v1\/2021.acl-long.456"},{"key":"957_CR29","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30. Curran Associates, Inc., Red Hook (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"957_CR30","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. 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 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"957_CR31","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized Bert pretraining approach. arXiv:abs\/1907.11692"},{"key":"957_CR32","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in neural information processing systems, vol 33, pp. 1877\u20131901. Curran Associates, Inc., Red Hook, NY. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"957_CR33","doi-asserted-by":"publisher","unstructured":"Shen J, Yin Y, Li L, Shang L, Jiang X, Zhang M, Liu Q (2021)Generate and rank: a multi-task framework for math word problems. In: Findings of the association for computational linguistics: EMNLP 2021, pp 2269\u20132279. Association for Computational Linguistics, Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.195","DOI":"10.18653\/v1\/2021.findings-emnlp.195"},{"key":"957_CR34","doi-asserted-by":"publisher","unstructured":"Liang Z., Zhang J, Wang L, Qin W, Lan Y, Shao J, Zhang X (2022) MWP-BERT: numeracy-augmented pre-training for math word problem solving. In: Carpuat M, Marneffe M-C, Meza\u00a0Ruiz IV (eds) Findings of the association for computational linguistics: NAACL 2022, pp 997\u20131009. Association for Computational Linguistics, Seattle, United States. https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.74","DOI":"10.18653\/v1\/2022.findings-naacl.74"},{"key":"957_CR35","doi-asserted-by":"publisher","unstructured":"Pi\u0119kos P, Malinowski M, Michalewski H (2021) Measuring and improving BERT\u2019s mathematical abilities by predicting the order of 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 2: short papers), pp 383\u2013394. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.acl-short.49","DOI":"10.18653\/v1\/2021.acl-short.49"},{"key":"957_CR36","unstructured":"Griffith K, Kalita J (2020) Solving arithmetic word problems using transformer and pre-processing of problem texts. In: Proceedings of the 17th international conference on natural language processing (ICON), pp 76\u201384. NLP Association of India (NLPAI), Indian Institute of Technology Patna, Patna, India. https:\/\/aclanthology.org\/2020.icon-main.10"},{"key":"957_CR37","doi-asserted-by":"publisher","unstructured":"Helwe C, Clavel C, Suchanek FM (2021) Reasoning with transformer-based models: Deep learning, but shallow reasoning. In: Chen D, Berant J, McCallum A, Singh S (eds) 3rd conference on automated knowledge base construction, AKBC 2021, Virtual, October 4-8. https:\/\/doi.org\/10.24432\/C5W300","DOI":"10.24432\/C5W300"},{"issue":"01","key":"957_CR38","doi-asserted-by":"publisher","first-page":"7297","DOI":"10.1609\/aaai.v33i01.33017297","volume":"33","author":"M Xia","year":"2019","unstructured":"Xia M, Huang G, Liu L, Shi S (2019) Graph based translation memory for neural machine translation. Proc AAAI Confer Artific Intell 33(01):7297\u20137304. https:\/\/doi.org\/10.1609\/aaai.v33i01.33017297","journal-title":"Proc AAAI Confer Artific Intell"},{"key":"957_CR39","doi-asserted-by":"publisher","unstructured":"Feng W, Liu B, Xu D, Zheng Q, Xu Y (2021) GraphMR: graph neural network for mathematical reasoning. In: Moens, M-F, Huang X, Specia L, Yih SW-t (eds) Proceedings of the 2021 conference on empirical methods in natural language processing, pp 3395\u20133404. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.273","DOI":"10.18653\/v1\/2021.emnlp-main.273"},{"key":"957_CR40","doi-asserted-by":"publisher","unstructured":"Li S, Wu L, Feng S, Xu F, Xu F, Zhong S (2020) Graph-to-tree neural networks for learning structured input-output translation with applications to semantic parsing and math word problem. In: Findings of the association for computational linguistics: EMNLP 2020, pp 2841\u20132852. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.255","DOI":"10.18653\/v1\/2020.findings-emnlp.255"},{"key":"957_CR41","doi-asserted-by":"publisher","unstructured":"Yu W, Wen Y, Zheng F, Xiao N (2021) Improving math word problems with pre-trained knowledge and hierarchical reasoning. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 3384\u20133394. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.272","DOI":"10.18653\/v1\/2021.emnlp-main.272"},{"key":"957_CR42","doi-asserted-by":"publisher","unstructured":"Xie Z, Sun S (2019) A goal-driven tree-structured neural model for math word problems. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19, pp 5299\u20135305 . https:\/\/doi.org\/10.24963\/ijcai.2019\/736","DOI":"10.24963\/ijcai.2019\/736"},{"issue":"5","key":"957_CR43","doi-asserted-by":"publisher","first-page":"4232","DOI":"10.1609\/aaai.v35i5.16547","volume":"35","author":"X Lin","year":"2021","unstructured":"Lin X, Huang Z, Zhao H, Chen E, Liu Q, Wang H, Wang S (2021) HMS: a hierarchical solver with dependency-enhanced understanding for math word problem. Proc AAAI Conferen Artific Intell 35(5):4232\u20134240. https:\/\/doi.org\/10.1609\/aaai.v35i5.16547","journal-title":"Proc AAAI Conferen Artific Intell"},{"key":"957_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114704","volume":"174","author":"K Zaporojets","year":"2021","unstructured":"Zaporojets K, Bekoulis G, Deleu J, Demeester T, Develder C (2021) Solving arithmetic word problems by scoring equations with recursive neural networks. Exp Syst Appl 174:114704. https:\/\/doi.org\/10.1016\/j.eswa.2021.114704","journal-title":"Exp Syst Appl"},{"key":"957_CR45","doi-asserted-by":"publisher","unstructured":"Wu Q, Zhang Q, Wei Z, Huang X (2021) Math word problem solving with explicit numerical values. 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 5859\u20135869. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.455","DOI":"10.18653\/v1\/2021.acl-long.455"},{"key":"957_CR46","doi-asserted-by":"publisher","unstructured":"Zhang J, Wang L, Lee RK-W, Bin Y, Wang Y, Shao J, Lim E-P (2020)Graph-to-tree learning for solving math word problems. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3928\u20133937. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.362","DOI":"10.18653\/v1\/2020.acl-main.362"},{"key":"957_CR47","doi-asserted-by":"publisher","unstructured":"Wu Q, Zhang Q, Fu J, Huang X (2020) A knowledge-aware sequence-to-tree network for math word problem solving. In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pp 7137\u20137146. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.579","DOI":"10.18653\/v1\/2020.emnlp-main.579"},{"key":"957_CR48","doi-asserted-by":"publisher","unstructured":"Zhang J, Lee RK-W, Lim E-P, Qin W, Wang L, Shao J, Sun Q (2020) Teacher-student networks with multiple decoders for solving math word problem. In: Bessiere C (ed) Proceedings of the twenty-ninth international joint conference on artificial intelligence, IJCAI-20, pp 4011\u20134017. https:\/\/doi.org\/10.24963\/ijcai.2020\/555 . Main track","DOI":"10.24963\/ijcai.2020\/555"},{"key":"957_CR49","doi-asserted-by":"publisher","unstructured":"Liang Z, Zhang X (2021) Solving math word problems with teacher supervision. In: Zhou Z-H (ed) Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21, pp 3522\u20133528. https:\/\/doi.org\/10.24963\/ijcai.2021\/485. Main Track","DOI":"10.24963\/ijcai.2021\/485"},{"key":"957_CR50","unstructured":"Koch G, Zemel R, Salakhutdinov R, et al (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, vol 2. Lille"},{"key":"957_CR51","doi-asserted-by":"publisher","unstructured":"Li Z, Zhang W, Yan C, Zhou Q, Li C, Liu H, Cao Y (2022) Seeking patterns, not just memorizing procedures: contrastive learning for solving math word problems. In: Findings of the association for computational linguistics: ACL 2022, pp 2486\u20132496. Association for Computational Linguistics, Dublin, Ireland. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.195","DOI":"10.18653\/v1\/2022.findings-acl.195"},{"issue":"6","key":"957_CR52","doi-asserted-by":"publisher","first-page":"4959","DOI":"10.1609\/aaai.v35i6.16629","volume":"35","author":"Y Hong","year":"2021","unstructured":"Hong Y, Li Q, Ciao D, Huang S, Zhu S-C (2021) Learning by fixing: Solving math word problems with weak supervision. Proc AAAI Confer Artific Intell 35(6):4959\u20134967. https:\/\/doi.org\/10.1609\/aaai.v35i6.16629","journal-title":"Proc AAAI Confer Artific Intell"},{"issue":"7","key":"957_CR53","doi-asserted-by":"publisher","first-page":"4715","DOI":"10.1007\/s11831-021-09552-3","volume":"28","author":"S Gupta","year":"2021","unstructured":"Gupta S, Singal G, Garg D (2021) Deep reinforcement learning techniques in diversified domains: a survey. Arch Comput Methods Eng 28(7):4715\u20134754. https:\/\/doi.org\/10.1007\/s11831-021-09552-3","journal-title":"Arch Comput Methods Eng"},{"key":"957_CR54","doi-asserted-by":"publisher","unstructured":"Wang L, Zhang D, Gao L, Song J, Guo L, Shen HT (2018) Mathdqn: solving arithmetic word problems via deep reinforcement learning. Proceedings of the AAAI conference on artificial intelligence, vol 32, no. 1. https:\/\/doi.org\/10.1609\/aaai.v32i1.11981","DOI":"10.1609\/aaai.v32i1.11981"},{"key":"957_CR55","unstructured":"Lu P, Qiu L, Chang K, Wu YN, Zhu S, Rajpurohit T, Clark P, Kalyan A (2023) Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning. In: The eleventh international conference on learning representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. https:\/\/openreview.net\/pdf?id=DHyHRBwJUTN"},{"issue":"2","key":"957_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100017","volume":"1","author":"Y Liu","year":"2023","unstructured":"Liu Y, Han T, Ma S, Zhang J, Yang Y, Tian J, He H, Li A, He M, Liu Z et al (2023) Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiology 1(2):100017. https:\/\/doi.org\/10.1016\/j.metrad.2023.100017","journal-title":"Meta-Radiology"},{"key":"957_CR57","unstructured":"Open AI, Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, et al (2023) GPT-4 Technical Report"},{"key":"957_CR58","unstructured":"Team G, Anil R, Borgeaud S, Wu Y, Alayrac J-B, Yu J, Soricut R, Schalkwyk J, Dai AM, Hauth A, et al (2023) Gemini: a family of highly capable multimodal models"},{"key":"957_CR59","unstructured":"Ahn J, Verma R, Lou R, Liu D, Zhang R, Yin W (2024) Large language models for mathematical reasoning: progresses and challenges"},{"key":"957_CR60","unstructured":"Liu W, Hu H, Zhou J, Ding Y, Li J, Zeng J, He M, Chen Q, Jiang B, Zhou A, et al (2023) Mathematical language models: a survey"},{"key":"957_CR61","unstructured":"Shakarian P, Koyyalamudi A, Ngu N, Mareedu L (2023) An independent evaluation of chatgpt on mathematical word problems (MWP). In: Proceedings of the AAAI 2023 spring symposium on challenges requiring the combination of machine learning and knowledge engineering (AAAI-MAKE 2023), Hyatt Regency, San Francisco Airport, California, USA, March 27-29, 2023. https:\/\/ceur-ws.org\/Vol-3433\/paper8.pdf"},{"key":"957_CR62","unstructured":"Wei T, Luan J, Liu W, Dong S, Wang B (2023) CMATH: can your language model pass Chinese elementary school math test?"},{"key":"957_CR63","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Ichter B., Xia F, Chi E, Le QV, Zhou D (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A (eds) Advances in neural information processing systems, vol 35, pp 24824\u201324837. Curran Associates, Inc., Red Hook. https:\/\/proceedings.neurips.cc\/paper%5Ffiles\/paper\/2022\/file\/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf"},{"key":"957_CR64","doi-asserted-by":"publisher","unstructured":"Zhang Y, Yang J, Yuan Y, Yao AC (2023) Cumulative reasoning with large language models. arxiv:abs\/2308.04371 (2023) https:\/\/doi.org\/10.48550\/arXiv.2308.04371","DOI":"10.48550\/arXiv.2308.04371"},{"key":"957_CR65","doi-asserted-by":"publisher","unstructured":"Imani S, Du L, Shrivastava H (2023) Mathprompter: mathematical reasoning using large language models. In: Proceedings of the The 61st annual meeting of the association for computational linguistics: Industry Track, ACL 2023, Toronto, Canada, July 9-14, 2023, pp 37\u201342. https:\/\/doi.org\/10.18653\/v1\/2023.acl-industry.4","DOI":"10.18653\/v1\/2023.acl-industry.4"},{"key":"957_CR66","unstructured":"Gou Z, Shao Z, Gong Y, shen Yang Y, Huang M, Duan N, Chen W (2023) ToRA: a tool-integrated reasoning agent for mathematical problem solving"},{"key":"957_CR67","unstructured":"Wu Y, Jia F, Zhang S, Li H, Zhu E, Wang Y, Lee YT, Peng R, Wu Q, Wang C (2023) An empirical study on challenging math problem solving with GPT-4"},{"key":"957_CR68","doi-asserted-by":"publisher","unstructured":"Zhao J, Xie Y, Kawaguchi K, He J, Xie M (2023) Automatic model selection with large language models for reasoning. In: Bouamor H, Pino J, Bali K (eds) Findings of the association for computational linguistics: EMNLP 2023, pp 758\u2013783. Association for Computational Linguistics, Singapore. https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.55","DOI":"10.18653\/v1\/2023.findings-emnlp.55"},{"key":"957_CR69","doi-asserted-by":"publisher","unstructured":"Zhou A, Wang K, Lu Z, Shi W, Luo S, Qin Z, Lu S, Jia A, Song L, Zhan M, et al (2023) Solving challenging math word problems using GPT-4 code interpreter with code-based self-verification. arxiv:abs\/2308.07921, https:\/\/doi.org\/10.48550\/arXiv.2308.07921","DOI":"10.48550\/arXiv.2308.07921"},{"key":"957_CR70","doi-asserted-by":"publisher","unstructured":"Zheng C, Liu Z, Xie E, Li Z, Li Y (2023) Progressive-hint prompting improves reasoning in large language models. arxiv:abs\/2304.09797, https:\/\/doi.org\/10.48550\/arxiv.2304.09797","DOI":"10.48550\/arxiv.2304.09797"},{"key":"957_CR71","doi-asserted-by":"publisher","unstructured":"Shi S, Wang Y, Lin C-Y, Liu X, Rui Y (2015) Automatically solving number word problems by semantic parsing and reasoning. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1132\u20131142. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/D15-1135","DOI":"10.18653\/v1\/D15-1135"},{"key":"957_CR72","unstructured":"Saxton D, Grefenstette E, Hill F, Kohli P (2019) Analysing mathematical reasoning abilities of neural models. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=H1gR5iR5FX"},{"key":"957_CR73","unstructured":"Lample G, Charton F (2020) Deep learning for symbolic mathematics. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=S1eZYeHFDS"},{"key":"957_CR74","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1162\/tacl_a_00160","volume":"3","author":"R Koncel-Kedziorski","year":"2015","unstructured":"Koncel-Kedziorski R, Hajishirzi H, Sabharwal A, Etzioni O, Ang SD (2015) Parsing algebraic word problems into equations. Trans Assoc Comput Linguist 3:585\u2013597. https:\/\/doi.org\/10.1162\/tacl_a_00160","journal-title":"Trans Assoc Comput Linguist"},{"key":"957_CR75","doi-asserted-by":"publisher","unstructured":"Roy S, Roth D (2015) Solving general arithmetic word problems. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1743\u20131752. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/D15-1202","DOI":"10.18653\/v1\/D15-1202"},{"key":"957_CR76","unstructured":"Zhao W, Shang M, Liu Y, Wang L, Liu J (2020) Ape210k: a large-scale and template-rich dataset of math word problems. ArXiv:abs\/2009.11506"},{"key":"957_CR77","doi-asserted-by":"publisher","unstructured":"Miao S, Liang C-C, Su K-Y (2020) 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. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.92","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"957_CR78","doi-asserted-by":"publisher","unstructured":"Koncel-Kedziorski R, Roy S, Amini A, Kushman N, Hajishirzi H (2016) MAWPS: A math word problem repository. In: Proceedings of the 2016 conference of the north american chapter of the association for computational linguistics: human language technologies, pp 1152\u20131157. Association for Computational Linguistics, San Diego, California. https:\/\/doi.org\/10.18653\/v1\/N16-1136","DOI":"10.18653\/v1\/N16-1136"},{"key":"957_CR79","doi-asserted-by":"publisher","unstructured":"Upadhyay S, Chang M-W, Chang K-W, Yih W-T (2016) Learning from explicit and implicit supervision jointly for algebra word problems. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 297\u2013306. Association for Computational Linguistics, Austin, Texas. https:\/\/doi.org\/10.18653\/v1\/D16-1029","DOI":"10.18653\/v1\/D16-1029"},{"key":"957_CR80","unstructured":"Anand A, Gupta M, Prasad K, Singla N, Sanjeev S, Kumar J, Shivam AR, Shah RR (2024) Mathify: evaluating large language models on mathematical problem solving tasks. NeurIPS"},{"key":"957_CR81","doi-asserted-by":"crossref","unstructured":"Yang Z, Qin J, Chen J, Lin L, Liang X (2022) LogicSolver: towards interpretable math word problem solving with logical prompt-enhanced learning. In: Findings of the association for computational linguistics: EMNLP 2022, pp 1\u201313. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/aclanthology.org\/2022.findings-emnlp.1","DOI":"10.18653\/v1\/2022.findings-emnlp.1"},{"key":"957_CR82","doi-asserted-by":"publisher","unstructured":"Patel A, Bhattamishra S, Goyal N (2021) 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. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.168","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"957_CR83","unstructured":"Cobbe K, Kosaraju V, Bavarian M, Hilton J, Nakano R, Hesse C, Schulman J (2021) Training verifiers to solve math word problems. ArXiv:abs\/2110.14168"},{"key":"957_CR84","doi-asserted-by":"crossref","unstructured":"Zhou Z, Wang Q, Jin M, Yao J, Ye J, Liu W, Wang W, Huang X, Huang K (2023) MathAttack: attacking large language models towards math solving ability","DOI":"10.1609\/aaai.v38i17.29949"},{"key":"957_CR85","unstructured":"Hendrycks D, Burns C, Kadavath S, Arora A, Basart S, Tang E, Song D, Steinhardt J (2021) Measuring mathematical problem solving with the MATH dataset. In: Proceedings of the neural information processing systems track on datasets and benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, Virtual. Curran Associates, Inc., Red Hook, NY. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/be83ab3ecd0db773eb2dc1b0a17836a1-Abstract-round2.html"},{"key":"957_CR86","doi-asserted-by":"crossref","unstructured":"Chen J, Li T, Qin J, Lu P, Lin L, Chen C, Liang X (2022) UniGeo: unifying geometry logical reasoning via reformulating mathematical expression. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 3313\u20133323. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/aclanthology.org\/2022.emnlp-main.218","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"957_CR87","doi-asserted-by":"publisher","unstructured":"Seo M, Hajishirzi H, Farhadi A, Etzioni O, Malcolm C (2015) Solving geometry problems: combining text and diagram interpretation. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1466\u20131476. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/D15-1171","DOI":"10.18653\/v1\/D15-1171"},{"key":"957_CR88","doi-asserted-by":"publisher","unstructured":"Lu P, Gong R, Jiang S, Qiu L, Huang S, Liang X, Zhu S-C (2021) 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. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.528","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"957_CR89","doi-asserted-by":"publisher","unstructured":"Hao Y, Zhang M, Yin F, Huang L-L (2022) Pgdp5k: a diagram parsing dataset for plane geometry problems. In: 2022 26th international conference on pattern recognition (ICPR), pp 1763\u20131769. https:\/\/doi.org\/10.1109\/icpr56361.2022.9956397","DOI":"10.1109\/icpr56361.2022.9956397"},{"key":"957_CR90","doi-asserted-by":"publisher","unstructured":"Zhang M-L, Yin F, Hao Y-H, Liu C-L (2022) Plane geometry diagram parsing. In: Raedt LD (ed) Proceedings of the thirty-first international joint conference on artificial intelligence, IJCAI-22, pp 1636\u20131643. https:\/\/doi.org\/10.24963\/ijcai.2022\/228 . Main Track. https:\/\/doi.org\/10.24963\/ijcai.2022\/228","DOI":"10.24963\/ijcai.2022\/228"},{"key":"957_CR91","doi-asserted-by":"publisher","unstructured":"Chen J, Tang J, Qin J, Liang X, Liu L, Xing E, Lin L (2021)GeoQA: a geometric question answering benchmark towards multimodal numerical reasoning. In: Findings of the association for computational linguistics: ACL-IJCNLP 2021, pp 513\u2013523. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.46","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"957_CR92","unstructured":"Cao J, Xiao J (2022) An augmented benchmark dataset for geometric question answering through dual parallel text encoding. In: Proceedings of the 29th international conference on computational linguistics, pp 1511\u20131520. International committee on computational linguistics, Gyeongju, Republic of Korea. https:\/\/aclanthology.org\/2022.coling-1.130"},{"key":"957_CR93","unstructured":"Lu P, Qiu L, Chen J, Xia T, Zhao Y, Zhang W, Yu Z, Liang X, Zhu S (2021) Iconqa: a new benchmark for abstract diagram understanding and visual language reasoning. In: Vanschoren J, Yeung S (eds) Proceedings of the neural information processing systems track on datasets and benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, Virtual. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/d3d9446802a44259755d38e6d163e820-Abstract-round2.html"},{"key":"957_CR94","unstructured":"Lindstr\u00f6m AD, Abraham SS (2022) Clevr-math: a dataset for compositional language, visual and mathematical reasoning. In: Garcez AS, Jim\u00e9nez-Ruiz E (eds) Proceedings of the 16th international workshop on neural-symbolic learning and reasoning as part of the 2nd international joint conference on learning & reasoning (IJCLR 2022), Cumberland Lodge, Windsor Great Park, UK, September 28-30, 2022. CEUR workshop proceedings, vol 3212, pp 155\u2013170 (2022). https:\/\/ceur-ws.org\/Vol-3212\/paper11.pdf"},{"key":"957_CR95","doi-asserted-by":"publisher","unstructured":"Johnson J, Hariharan B, Maaten L, Fei-Fei L, Zitnick CL, Girshick R (2017) Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1988\u20131997. https:\/\/doi.org\/10.1109\/CVPR.2017.215","DOI":"10.1109\/CVPR.2017.215"},{"key":"957_CR96","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, et al (2021) Learning transferable visual models from natural language supervision. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning. Proceedings of machine learning research, vol 139, pp 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"957_CR97","unstructured":"Yi K, Wu J, Gan C, Torralba A, Kohli P, Tenenbaum J (2018) Neural-symbolic vqa: disentangling reasoning from vision and language understanding. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems, vol 31. Curran Associates, Inc., Red Hook, NY. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/5e388103a391daabe3de1d76a6739ccd-Paper.pdf"},{"key":"957_CR98","doi-asserted-by":"publisher","unstructured":"Zhao Y, Li Y, Li C, Zhang R (2022) MltiHiertt: numerical reasoning over multi hierarchical tabular and textual data. In: Muresan S, Nakov P, Villavicencio A (eds) Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers), pp 6588\u20136600. Association for Computational Linguistics, Dublin, Ireland. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.454 . https:\/\/aclanthology.org\/2022.acl-long.454","DOI":"10.18653\/v1\/2022.acl-long.454"},{"key":"#cr-split#-957_CR99.1","doi-asserted-by":"crossref","unstructured":"Joshi A, Kajale A, Gadre J, Deode S, Joshi R (2023) L3cube-mahasbert and hindsbert: sentence bert models and benchmarking bert sentence representations for hindi and marathi. In: Arai K","DOI":"10.1007\/978-3-031-37963-5_82"},{"key":"#cr-split#-957_CR99.2","unstructured":"(ed) Proceedings of the 2023 computing conference, volume 2, intelligent computing, pp 1184-1199. Springer, Cham"},{"key":"957_CR100","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14273-1","author":"A Jha","year":"2022","unstructured":"Jha A, Patil HY (2022) A review of machine transliteration, translation, evaluation metrics and datasets in Indian languages. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-022-14273-1","journal-title":"Multimed Tools Appl"},{"key":"957_CR101","doi-asserted-by":"publisher","unstructured":"Kakwani D, Kunchukuttan A, Golla S, NC G, Bhattacharyya A, Khapra MM, Kumar P (2020) IndicNLPSuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In: Findings of the association for computational linguistics: EMNLP 2020, pp 4948\u20134961. Association for computational linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.445. https:\/\/aclanthology.org\/2020.findings-emnlp.445","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"957_CR102","doi-asserted-by":"crossref","unstructured":"Kumar A, Shrotriya H, Sahu P, Mishra A, Dabre R, Puduppully R, Kunchukuttan A, Khapra MM, Kumar P (2022) IndicNLG benchmark: multilingual datasets for diverse NLG tasks in Indic languages. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 5363\u20135394. Association for computational linguistics, Abu Dhabi, United Arab Emirates. https:\/\/aclanthology.org\/2022.emnlp-main.360","DOI":"10.18653\/v1\/2022.emnlp-main.360"},{"key":"957_CR103","doi-asserted-by":"crossref","unstructured":"Aggarwal D, Gupta V, Kunchukuttan A (2022) IndicXNLI: evaluating multilingual inference for Indian languages. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 10994\u201311006. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/aclanthology.org\/2022.emnlp-main.755","DOI":"10.18653\/v1\/2022.emnlp-main.755"},{"key":"957_CR104","unstructured":"Alghamdi R, Liang Z, Zhang X (2022) ArMATH: a dataset for solving Arabic math word problems. In: Calzolari N, B\u00e9chet F, Blache P, Choukri K, Cieri C, Declerck T, Goggi S, Isahara H, Maegaard B, Mariani J, Mazo H, Odijk J, Piperidis S (eds) Proceedings of the thirteenth language resources and evaluation conference, pp 351\u2013362. European Language Resources Association, Marseille, France. https:\/\/aclanthology.org\/2022.lrec-1.37"},{"key":"957_CR105","unstructured":"Sharma H, Mishra P, Sharma D (2022) HAWP: a dataset for Hindi arithmetic word problem solving. In: Proceedings of the thirteenth language resources and evaluation conference, pp 3479\u20133490. European Language Resources Association, Marseille, France. https:\/\/aclanthology.org\/2022.lrec-1.373"},{"key":"957_CR106","doi-asserted-by":"publisher","unstructured":"Liang C-C, Wong Y-S, Lin Y-C, Su K-Y (2018) A meaning-based statistical English math word problem solver. In: Proceedings of the 2018 conference of the north American chapter of the association for computational linguistics: human language technologies, volume 1 (long papers), pp 652\u2013662. Association for Computational Linguistics, New Orleans, Louisiana. https:\/\/doi.org\/10.18653\/v1\/N18-1060 . https:\/\/aclanthology.org\/N18-1060","DOI":"10.18653\/v1\/N18-1060"},{"key":"957_CR107","doi-asserted-by":"publisher","unstructured":"Gaur V, Saunshi N (2023) Reasoning in large language models through symbolic math word problems. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the association for computational linguistics: ACL 2023, pp 5889\u20135903. Association for Computational Linguistics, Toronto, Canada. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.364","DOI":"10.18653\/v1\/2023.findings-acl.364"},{"key":"957_CR108","doi-asserted-by":"publisher","unstructured":"Zhang W, Shen Y, Ma Y, Cheng X, Tan Z, Nong Q, Lu W (2022) Multi-view reasoning: consistent contrastive learning for math word problem. In: Goldberg Y, Kozareva Z, Zhang Y (eds) Findings of the association for computational linguistics: EMNLP 2022, pp 1103\u20131116. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.79","DOI":"10.18653\/v1\/2022.findings-emnlp.79"},{"key":"957_CR109","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Jurafsky D, Chai J, Schluter N, Tetreault J (eds) Proceedings of the 58th annual meeting of the association for computational linguistics, pp 7871\u20137880. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"957_CR110","doi-asserted-by":"publisher","unstructured":"Huang S, Wang J, Xu J, Cao D, Yang M (2021) Recall and learn: a memory-augmented solver for math word problems. In: Findings of the association for computational linguistics: EMNLP 2021, pp 786\u2013796. Association for Computational Linguistics, Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.68","DOI":"10.18653\/v1\/2021.findings-emnlp.68"},{"key":"957_CR111","doi-asserted-by":"publisher","unstructured":"See A, Liu PJ (2017) Manning CD Get to the point: summarization with pointer-generator networks. In: Barzilay R, Kan M-Y (eds) Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers), pp 1073\u20131083. Association for Computational Linguistics, Vancouver, Canada. https:\/\/doi.org\/10.18653\/v1\/P17-1099","DOI":"10.18653\/v1\/P17-1099"},{"key":"957_CR112","doi-asserted-by":"crossref","unstructured":"Huang S, Wang J, Xu J, Cao D, Yang M (2021) Real2: an end-to-end memory-augmented solver for math word problems. In: Workshop on math AI for education (MATHAI4ED), 35th conference on neural information processing systems (NeurIPS 2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.68"},{"key":"957_CR113","doi-asserted-by":"publisher","unstructured":"Jie Z, Li J, Lu W (2022) Learning to reason deductively: math word problem solving as complex relation extraction. In: Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers), pp 5944\u20135955. Association for Computational Linguistics, Dublin, Ireland. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.410","DOI":"10.18653\/v1\/2022.acl-long.410"},{"key":"957_CR114","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. In: Oh AH, Agarwal A, Belgrave D, Cho K (eds) Advances in neural information processing systems. https:\/\/openreview.net\/forum?id=e2TBb5y0yFf"},{"key":"957_CR115","doi-asserted-by":"publisher","unstructured":"Toshniwal S, Moshkov I, Narenthiran S, Gitman D, Jia F, Gitman I (2024) Openmathinstruct-1: a 1.8 million math instruction tuning dataset. arxiv:abs\/2402.10176, https:\/\/doi.org\/10.48550\/arxiv.2402.10176","DOI":"10.48550\/arxiv.2402.10176"},{"key":"957_CR116","unstructured":"Lewkowycz A, Andreassen A, Dohan D, Dyer E, Michalewski H, Ramasesh V, Slone A, Anil C, Schlag I, Gutman-Solo T, et al (2022) Solving quantitative reasoning problems with language models. In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A (eds) Advances in neural information processing systems, vol 35, pp 3843\u20133857. Curran Associates, Inc., Red Hook. https:\/\/proceedings.neurips.cc\/paper%5Ffiles\/paper\/2022\/file\/18abbeef8cfe9203fdf9053c9c4fe191-Paper-Conference.pdf"},{"issue":"11","key":"957_CR117","doi-asserted-by":"publisher","first-page":"13188","DOI":"10.1609\/aaai.v36i11.21723","volume":"36","author":"Y Lan","year":"2022","unstructured":"Lan Y, Wang L, Zhang Q, Lan Y, Dai BT, Wang Y, Zhang D, Lim E-P (2022) Mwptoolkit: an open-source framework for deep learning-based math word problem solvers. Proc AAAI Confer Artificial Intell 36(11):13188\u201313190. https:\/\/doi.org\/10.1609\/aaai.v36i11.21723","journal-title":"Proc AAAI Confer Artificial Intell"},{"key":"957_CR118","doi-asserted-by":"crossref","unstructured":"Mishra S, Finlayson M, Lu P, Tang L, Welleck S, Baral C, Rajpurohit T, Tafjord O, Sabharwal A, Clark P, et al (2022) LILA: a unified benchmark for mathematical reasoning. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 5807\u20135832. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates. https:\/\/aclanthology.org\/2022.emnlp-main.392","DOI":"10.18653\/v1\/2022.emnlp-main.392"},{"key":"957_CR119","doi-asserted-by":"publisher","unstructured":"Kiela D, Bartolo M, Nie Y, Kaushik D, Geiger A, Wu Z, Vidgen B, Prasad G, Singh A, Ringshia P, et al (2021) Dynabench: rethinking benchmarking in NLP. In: Proceedings of the 2021 Conference of the North American chapter of the association for computational linguistics: human language technologies, pp 4110\u20134124. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.324","DOI":"10.18653\/v1\/2021.naacl-main.324"}],"container-title":["Evolutionary Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-024-00957-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12065-024-00957-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-024-00957-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T06:17:39Z","timestamp":1729318659000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12065-024-00957-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":120,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["957"],"URL":"https:\/\/doi.org\/10.1007\/s12065-024-00957-0","relation":{},"ISSN":["1864-5909","1864-5917"],"issn-type":[{"value":"1864-5909","type":"print"},{"value":"1864-5917","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,8]]},"assertion":[{"value":"7 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"All authors consent for the publication of the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}