{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:15:51Z","timestamp":1757618151544,"version":"3.44.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62177024"],"award-info":[{"award-number":["62177024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"self-determined research funds of CCNU from the colleges' basic research and operation of MOE","award":["30106230029"],"award-info":[{"award-number":["30106230029"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00521-025-11366-4","type":"journal-article","created":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T07:47:28Z","timestamp":1748764048000},"page":"16327-16348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bayesian math word problem solvers with credibility level: know what they know and what they do not know"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7615-010X","authenticated-orcid":false,"given":"Shengbing","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinguo","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,1]]},"reference":[{"key":"11366_CR1","doi-asserted-by":"crossref","unstructured":"Lu P, Qiu L, Yu W, et al (2023) A survey of deep learning for mathematical reasoning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Long Papers), vol 1, pp 14605\u201314631","DOI":"10.18653\/v1\/2023.acl-long.817"},{"key":"11366_CR2","doi-asserted-by":"crossref","unstructured":"Qiao S, Ou Y, Zhang N, et al (2023) Reasoning with language model prompting: a survey. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Long Papers), vol 1, pp 5368\u20135393","DOI":"10.18653\/v1\/2023.acl-long.294"},{"issue":"9","key":"11366_CR3","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1109\/TPAMI.2019.2914054","volume":"42","author":"D Zhang","year":"2019","unstructured":"Zhang D, Wang L, Zhang L et al (2019) The gap of semantic parsing: a survey on automatic math word problem solvers. IEEE Trans Pattern Anal Mach Intell 42(9):2287\u20132305","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11366_CR4","doi-asserted-by":"crossref","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","DOI":"10.18653\/v1\/D17-1088"},{"key":"11366_CR5","doi-asserted-by":"crossref","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, pp 5299\u20135305","DOI":"10.24963\/ijcai.2019\/736"},{"key":"11366_CR6","doi-asserted-by":"crossref","unstructured":"Wang L, Wang Y, Cai D, et al (2018) Translating a math word problem to a expression tree. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 1064\u20131069","DOI":"10.18653\/v1\/D18-1132"},{"key":"11366_CR7","doi-asserted-by":"crossref","unstructured":"Liu Q, Guan W, Li S, et al (2019) Tree-structured decoding for solving math word problems. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 2370\u20132379","DOI":"10.18653\/v1\/D19-1241"},{"key":"11366_CR8","doi-asserted-by":"crossref","unstructured":"Liang Z, Zhang J, Wang L et al (2022) MWP-BERT: numeracy-augmented pre-training for math word problem solving. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp 997\u20131009","DOI":"10.18653\/v1\/2022.findings-naacl.74"},{"key":"11366_CR9","unstructured":"Devlin J, Chang M, Lee K, et al (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, vol 1, pp 4171\u20134186"},{"key":"11366_CR10","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"issue":"240","key":"11366_CR11","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery A, Narang S, Devlin J et al (2023) Palm: scaling language modeling with pathways. J Mach Learn Res 24(240):1\u2013113","journal-title":"J Mach Learn Res"},{"key":"11366_CR12","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, et al (2020) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 7871\u20137880","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"11366_CR13","unstructured":"Cobbe K, Kosaraju V, Bavarian M, et al (2021) Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168"},{"key":"11366_CR14","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu Y, Gu J, Goyal N et al (2020) Multilingual denoising pre-training for neural machine translation. Trans Assoc Comput Linguist 8:726\u2013742","journal-title":"Trans Assoc Comput Linguist"},{"key":"11366_CR15","doi-asserted-by":"crossref","unstructured":"Shen J, Yin Y, Li L et al (2021) Generate & Rank: a multi-task framework for math word problems. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp 2269\u20132279","DOI":"10.18653\/v1\/2021.findings-emnlp.195"},{"key":"11366_CR16","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D et al (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst 35:24824\u201324837","journal-title":"Adv Neural Inf Process Syst"},{"key":"11366_CR17","doi-asserted-by":"crossref","unstructured":"Rubin O, Herzig J, Berant J (2022) Learning To retrieve prompts for in-context learning. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 2655\u20132671","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"11366_CR18","doi-asserted-by":"crossref","unstructured":"Liu J, Shen D, Zhang Y, et al (2022) What makes good in-context examples for GPT-3?. In: Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pp 100\u2013114","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"11366_CR19","unstructured":"Zhang Z, Zhang A, Li M, et al (2022) Automatic chain of thought prompting in large language models. In: The Eleventh International Conference on Learning Representations"},{"key":"11366_CR20","unstructured":"Diao S, Wang P, Lin Y, et al (2023) Active prompting with chain-of-thought for large language models. arXiv preprint arXiv:2302.12246"},{"key":"11366_CR21","unstructured":"Fu Y, Peng H, Sabharwal A, et al (2022) Complexity-based prompting for multi-step reasoning. In: The Eleventh International Conference on Learning Representations"},{"key":"11366_CR22","unstructured":"Chen M, Tworek J, Jun H, et al (2021) Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374"},{"key":"11366_CR23","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: International conference on machine learning, pp 1050\u20131059"},{"key":"11366_CR24","unstructured":"Hoffmann L, Elster C (2021) Deep ensembles from a bayesian perspective. arXiv preprint arXiv:2105.13283"},{"issue":"2","key":"11366_CR25","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MCI.2022.3155327","volume":"17","author":"LV Jospin","year":"2022","unstructured":"Jospin LV, Laga H, Boussaid F, Buntine W, Bennamoun M (2022) Hands-on Bayesian neural networks-A tutorial for deep learning users. IEEE Comput Intell Mag 17(2):29\u201348","journal-title":"IEEE Comput Intell Mag"},{"key":"11366_CR26","unstructured":"Wu Y, Schuster M, Chen Z, Le Q, Norouzi M (2016) Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144"},{"key":"11366_CR27","unstructured":"Gal Y (2016) Uncertainty in Deep Learning, PhD thesis, University of Cambridge"},{"key":"11366_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109553","volume":"139","author":"Z Wang","year":"2025","unstructured":"Wang Z, Duan J, Yuan C, Chen Q, Chen T, Zhang Y, Wang R, Shi X, Xu K (2025) Word-sequence entropy: towards uncertainty estimation in free-form medical question answering applications and beyond. Eng Appl Artif Intell 139:109553","journal-title":"Eng Appl Artif Intell"},{"key":"11366_CR29","unstructured":"Aichberger L, Schweighofer K, Ielanskyi M, Hochreiter S (2024) Semantically diverse language generation for uncertainty estimation in language models. arXiv preprint arXiv:2406.04306"},{"key":"11366_CR30","unstructured":"Amini A, Gabriel S, Lin S, et al (2019) 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, vol 1, pp 2357\u201312367"},{"key":"11366_CR31","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 preprint arXiv:2009.11506"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11366-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11366-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11366-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T17:15:46Z","timestamp":1757178946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11366-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":31,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11366"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11366-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2025,6,1]]},"assertion":[{"value":"25 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that this manuscript is original, has not been published before and is not currently being considered for publication elsewhere. We confirm that the manuscript has been read and approved by all named authors and that there are no other persons who satisfied the criteria for authorship but are not listed. We further confirm that the order of authors listed in the manuscript has been approved by all of us.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}},{"value":"The authors declare the following financial interests\/personal relationships which may be considered as potential conflict of interest: Bin He reports financial support was provided by National Natural Science Foundation of China under Grant 62177024. Shengbing Tang reports financial support was provided by self-determined research funds of CCNU from the colleges\u2019 basic research and operation of MOE [Central China Normal University, Grant No. 30106230029].","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}