{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:42:27Z","timestamp":1740109347580,"version":"3.37.3"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:00:00Z","timestamp":1725580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:00:00Z","timestamp":1725580800000},"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":["62072224"],"award-info":[{"award-number":["62072224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10115-024-02216-1","type":"journal-article","created":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T10:34:34Z","timestamp":1725618874000},"page":"197-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Targeted training for numerical reasoning with large language models"],"prefix":"10.1007","volume":"67","author":[{"given":"Xiao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sichen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,6]]},"reference":[{"key":"2216_CR1","unstructured":"Frieder S, Pinchetti L, Griffiths R-R, Salvatori T, Lukasiewicz T, Petersen PC, Chevalier A, Berner J (2023) Mathematical capabilities of chatgpt. arXiv preprint arXiv:2301.13867"},{"key":"2216_CR2","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi EH, Le QV, Zhou D, et al (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Advances in neural information processing systems"},{"key":"2216_CR3","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. In: Advances in neural information processing systems"},{"key":"2216_CR4","doi-asserted-by":"publisher","unstructured":"Qiao S, Ou Y, Zhang N, Chen X, Yao Y, Deng S, Tan C, Huang F, Chen H (2023) Reasoning with language model prompting: A survey. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5368\u20135393. Association for Computational Linguistics, Toronto, Canada. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.294. https:\/\/aclanthology.org\/2023.acl-long.294","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"2216_CR5","unstructured":"Cobbe K, Kosaraju V, Bavarian M, Chen M, Jun H, Kaiser L, Plappert M, Tworek J, Hilton J, Nakano R et al (2021) Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168"},{"key":"2216_CR6","unstructured":"Muffo M, Cocco A, Bertino E (2022) Evaluating transformer language models on arithmetic operations using number decomposition. In: Proceedings of the thirteenth language resources and evaluation conference. European Language Resources Association, Marseille, France, pp. 291\u2013297. https:\/\/aclanthology.org\/2022.lrec-1.30"},{"key":"2216_CR7","unstructured":"Yuan Z, Yuan H, Tan C, Wang W, Huang S (2023) How well do large language models perform in arithmetic tasks? arXiv preprint arXiv:2304.02015"},{"key":"2216_CR8","unstructured":"Fu Y, Peng H, Ou L, Sabharwal A, Khot T (2023) Specializing smaller language models towards multi-step reasoning. In: International conference on machine learning. PMLR"},{"key":"2216_CR9","doi-asserted-by":"crossref","unstructured":"Magister LC, Mallinson J, Adamek J, Malmi E, Severyn A (2022) Teaching small language models to reason. arXiv preprint arXiv:2212.08410","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"2216_CR10","doi-asserted-by":"publisher","unstructured":"Shridhar K, Stolfo A, Sachan M (2023) Distilling reasoning capabilities into smaller language models. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the association for computational linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, pp 7059\u20137073 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.441. https:\/\/aclanthology.org\/2023.findings-acl.441","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"2216_CR11","unstructured":"Zhu X, Qi B, Zhang K, Long X, Zhou B (2023) Pad: Program-aided distillation specializes large models in reasoning. arXiv preprint arXiv:2305.13888"},{"key":"2216_CR12","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. Association for Computational Linguistics, Lisbon, Portugal, pp 1743\u20131752. https:\/\/doi.org\/10.18653\/v1\/D15-1202. https:\/\/aclanthology.org\/D15-1202","DOI":"10.18653\/v1\/D15-1202"},{"key":"2216_CR13","doi-asserted-by":"publisher","unstructured":"Miao S-y, 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. Association for Computational Linguistics, pp 975\u2013984. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.92. https:\/\/aclanthology.org\/2020.acl-main.92","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"2216_CR14","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. Association for Computational Linguistics, pp 2080\u20132094 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.168. https:\/\/aclanthology.org\/2021.naacl-main.168","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"2216_CR15","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/tacl_a_00012","volume":"6","author":"S Roy","year":"2018","unstructured":"Roy S, Roth D (2018) Mapping to declarative knowledge for word problem solving. Trans Assoc Comput Linguist 6:159\u2013172. https:\/\/doi.org\/10.1162\/tacl_a_00012","journal-title":"Trans Assoc Comput Linguist"},{"key":"2216_CR16","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. Association for Computational Linguistics, San Diego, California, pp 1152\u20131157. https:\/\/doi.org\/10.18653\/v1\/N16-1136. https:\/\/aclanthology.org\/N16-1136","DOI":"10.18653\/v1\/N16-1136"},{"key":"2216_CR17","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, pp 535\u2013541","DOI":"10.1145\/1150402.1150464"},{"key":"2216_CR18","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"issue":"11","key":"2216_CR19","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1007\/s10115-022-01736-y","volume":"64","author":"M Ryu","year":"2022","unstructured":"Ryu M, Lee G, Lee K (2022) Knowledge distillation for bert unsupervised domain adaptation. Knowl Inf Syst 64(11):3113\u20133128","journal-title":"Knowl Inf Syst"},{"key":"2216_CR20","doi-asserted-by":"publisher","unstructured":"Ho N, Schmid L, Yun S-Y (2023) Large language models are reasoning teachers. 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). Association for Computational Linguistics, Toronto, Canada, pp 14852\u201314882 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.830 . https:\/\/aclanthology.org\/2023.acl-long.830","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"2216_CR21","doi-asserted-by":"crossref","unstructured":"Hsieh C-Y, Li C-L, Yeh C-K, Nakhost H, Fujii Y, Ratner A, Krishna R, Lee C-Y, Pfister T (2023) Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"2216_CR22","unstructured":"Marx E, Coelho C (2017) Answering live questions from heterogeneous data sources smart in live QA at TREC 2016. https:\/\/api.semanticscholar.org\/CorpusID:16195076"},{"key":"2216_CR23","doi-asserted-by":"publisher","unstructured":"Yang Z, Qi P, Zhang S, Bengio Y, Cohen W, Salakhutdinov R, Manning CD (2018) HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Proceedings of the 2018 conference on empirical methods in natural language processing. Association for Computational Linguistics, Brussels, Belgium, pp 2369\u20132380. https:\/\/doi.org\/10.18653\/v1\/D18-1259. https:\/\/aclanthology.org\/D18-1259","DOI":"10.18653\/v1\/D18-1259"},{"key":"2216_CR24","doi-asserted-by":"crossref","unstructured":"Deng W, Wang Z, Wang K, Zhang X, Feng Z (2022) Choice-driven contextual reasoning for commonsense question answering. In: Pacific Rim international conference on artificial intelligence (2022). https:\/\/api.semanticscholar.org\/CorpusID:253386545","DOI":"10.1007\/978-3-031-20865-2_25"},{"key":"2216_CR25","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1109\/TASLP.2022.3164218","volume":"30","author":"S Wang","year":"2022","unstructured":"Wang S, Liu Z, Zhong W, Zhou M, Wei Z, Chen Z, Duan N (2022) From LSAT: the progress and challenges of complex reasoning. IEEE\/ACM Trans Audio Speech Lang Process 30:2201\u20132216. https:\/\/doi.org\/10.1109\/TASLP.2022.3164218","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"2216_CR26","doi-asserted-by":"crossref","unstructured":"Su\u00e1rez F, Hogan A (2023) Templet: a collaborative system for knowledge graph question answering over Wikidata. In: Companion proceedings of the ACM web conference 2023","DOI":"10.1145\/3543873.3587335"},{"issue":"4","key":"2216_CR27","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1007\/s10115-022-01783-5","volume":"65","author":"H Abdel-Nabi","year":"2023","unstructured":"Abdel-Nabi H, Awajan A, Ali MZ (2023) Deep learning-based question answering: a survey. Knowl Inf Syst 65(4):1399\u20131485","journal-title":"Knowl Inf Syst"},{"key":"2216_CR28","doi-asserted-by":"publisher","unstructured":"Hosseini MJ, Hajishirzi H, Etzioni O, Kushman N (2014) Learning to solve arithmetic word problems with verb categorization. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, Doha, Qatar, pp 523\u2013533 (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1058. https:\/\/aclanthology.org\/D14-1058","DOI":"10.3115\/v1\/D14-1058"},{"key":"2216_CR29","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). Association for Computational Linguistics, Berlin, Germany, pp 887\u2013896. https:\/\/doi.org\/10.18653\/v1\/P16-1084. https:\/\/aclanthology.org\/P16-1084","DOI":"10.18653\/v1\/P16-1084"},{"key":"2216_CR30","doi-asserted-by":"publisher","unstructured":"Kushman N, Artzi Y, Zettlemoyer L, Barzilay R (2014) Learning to automatically solve algebra word problems. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Baltimore, Maryland, pp 271\u2013281 (2014). https:\/\/doi.org\/10.3115\/v1\/P14-1026. https:\/\/aclanthology.org\/P14-1026","DOI":"10.3115\/v1\/P14-1026"},{"key":"2216_CR31","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. Association for Computational Linguistics, Lisbon, Portugal, pp 1132\u20131142. https:\/\/doi.org\/10.18653\/v1\/D15-1135 . https:\/\/aclanthology.org\/D15-1135","DOI":"10.18653\/v1\/D15-1135"},{"key":"2216_CR32","doi-asserted-by":"crossref","unstructured":"Wang L, Zhang D, Zhang J, Xu X, Gao L, Dai BT, Shen HT (2019) Template-based math word problem solvers with recursive neural networks. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 7144\u20137151","DOI":"10.1609\/aaai.v33i01.33017144"},{"key":"2216_CR33","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: 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). Association for Computational Linguistics, pp 5870\u20135881. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.456. https:\/\/aclanthology.org\/2021.acl-long.456","DOI":"10.18653\/v1\/2021.acl-long.456"},{"key":"2216_CR34","doi-asserted-by":"publisher","unstructured":"Shen J, Yin Y, Li L, Shang L, Jiang X, Zhang M, Liu Q (2021) Generate & rank: a multi-task framework for math word problems. In: Findings of the association for computational linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, pp 2269\u20132279. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.294.https:\/\/aclanthology.org\/2023.acl-long.294","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"2216_CR35","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). Association for Computational Linguistics, Dublin, Ireland, pp. 5944\u20135955. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.410 . https:\/\/aclanthology.org\/2022.acl-long.410","DOI":"10.18653\/v1\/2022.acl-long.410"},{"issue":"3","key":"2216_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103324","volume":"60","author":"J Xiao","year":"2023","unstructured":"Xiao J, Huang L, Song Y, Tang N (2023) A recursive tree-structured neural network with goal forgetting and information aggregation for solving math word problems. Inf Process Manag 60(3):103324. https:\/\/doi.org\/10.1016\/j.ipm.2023.103324","journal-title":"Inf Process Manag"},{"key":"2216_CR37","doi-asserted-by":"crossref","unstructured":"Lyu Q, Havaldar S, Stein A, Zhang L, Rao D, Wong E, Apidianaki M, Callison-Burch C (2023) Faithful chain-of-thought reasoning. arXiv preprint arXiv:2301.13379","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"2216_CR38","unstructured":"Yao S, Yu D, Zhao J, Shafran I, Griffiths TL, Cao Y, Narasimhan K (2023) Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601"},{"key":"2216_CR39","unstructured":"Gao L, Madaan A, Zhou S, Alon U, Liu P, Yang Y, Callan J, Neubig G (2022) PAL: program-aided language models. arXiv preprint arXiv:2211.10435"},{"key":"2216_CR40","unstructured":"Schick T, Dwivedi-Yu J, Dess\u00ec R, Raileanu R, Lomeli M, Zettlemoyer L, Cancedda N, Scialom T (2023) Toolformer: language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761"},{"key":"2216_CR41","unstructured":"Wang X, Wei J, Schuurmans D, Le QV, Chi EH, Narang S, Chowdhery A, Zhou D (2023) Self-consistency improves chain of thought reasoning in language models. In: The eleventh international conference on learning representations. https:\/\/openreview.net\/forum?id=1PL1NIMMrw"},{"key":"2216_CR42","doi-asserted-by":"crossref","unstructured":"Khalifa M, Logeswaran L, Lee M, Lee H, Wang L (2023) Grace: Discriminator-guided chain-of-thought reasoning. In: Findings of the association for computational linguistics: EMNLP 2023, pp 15299\u201315328","DOI":"10.18653\/v1\/2023.findings-emnlp.1022"},{"key":"2216_CR43","doi-asserted-by":"crossref","unstructured":"Hu Z, Lan Y, Wang L, Xu W, Lim E-P, Lee RK-W, Bing L, Poria S (2023) Llm-adapters: an adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"2216_CR44","doi-asserted-by":"crossref","unstructured":"Xi Z, Jin S, Zhou Y, Zheng R, Gao S, Gui T, Zhang Q, Huang X (2023) Self-polish: enhance reasoning in large language models via problem refinement. arXiv preprint arXiv:2305.14497","DOI":"10.18653\/v1\/2023.findings-emnlp.762"},{"key":"2216_CR45","unstructured":"Zhou D, Sch\u00e4rli N, Hou L, Wei J, Scales N, Wang X, Schuurmans D, Cui C, Bousquet O, Le QV, Chi EH (2023) Least-to-most prompting enables complex reasoning in large language models. In: The eleventh international conference on learning representations. https:\/\/openreview.net\/forum?id=WZH7099tgfM"},{"key":"2216_CR46","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. arXiv preprint arXiv:2210.17517","DOI":"10.18653\/v1\/2022.emnlp-main.392"},{"key":"2216_CR47","unstructured":"Shen Y, Sanghavi S (2019) Learning with bad training data via iterative trimmed loss minimization. In: International conference on machine learning. PMLR, pp 5739\u20135748"},{"key":"2216_CR48","doi-asserted-by":"crossref","unstructured":"Bang Y, Cahyawijaya S, Lee N, Dai W, Su D, Wilie B, Lovenia H, Ji Z, Yu T, Chung W, et al (2023) A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"issue":"1","key":"2216_CR49","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(1):5485\u20135551","journal-title":"J Mach Learn Res"},{"key":"2216_CR50","unstructured":"Chung HW, Hou L, Longpre S, Zoph B, Tay Y, Fedus W, Li E, Wang X, Dehghani M, Brahma S et al (2022) Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416"},{"key":"2216_CR51","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S et al (2023) Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"2216_CR52","unstructured":"Contributors O (2023) OpenCompass: a universal evaluation platform for foundation models. https:\/\/github.com\/open-compass\/opencompass"},{"key":"2216_CR53","unstructured":"OpenAI: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"2216_CR54","unstructured":"Anthropic: Claude. https:\/\/www.anthropic.com\/ (2023)"},{"key":"2216_CR55","unstructured":"Bai J, Bai S, Chu Y, Cui Z, Dang K, Deng X, Fan Y, Ge W, Han Y, Huang F, Hui B, Ji L, Li M, Lin J, Lin R, Liu D, Liu G, Lu C, Lu K, Ma J, Men R, Ren X, Ren X, Tan C, Tan S, Tu J, Wang P, Wang S, Wang W, Wu S, Xu B, Xu J, Yang A, Yang H, Yang J, Yang J, Yang S, Yao Y, Yu B, Bowen Y, Yuan H, Yuan Z, Zhang J, Zhang X, Zhang Y, Zhang Z, Zhou C, Zhou J, Zhou X, Zhu T (2023) Qwen technical report. arXiv:2309.16609"},{"key":"2216_CR56","unstructured":"Bi D-AX, Chen D, Chen G, Chen S, Dai D, Deng C, Ding H, Dong K, Du Q, Fu Z, Gao H, Gao K, Gao W, Ge R, Guan K, Guo D, Guo J, Hao G, Hao Z, He Y, Hu W-H, Huang P, Li E, Li G, Li J, Li Y, Li YK, Liang W, Lin F, Liu AX, Liu B, Liu W, Liu X, Liu X, Liu Y, Lu H, Lu S, Luo F, Ma S, Nie X, Pei T, Piao Y, Qiu J, Qu H, Ren T, Ren Z, Ruan C, Sha Z, Shao Z, Song J-M, Su X, Sun J, Sun Y, Tang M, Wang B-L, Wang P, Wang S, Wang Y, Wang Y, Wu T, Wu Y, Xie X, Xie Z, Xie Z, Xiong Y, Xu H, Xu RX, Xu Y, Yang D, You Y-m, Yu S, Yu X-y, Zhang B, Zhang H, Zhang L, Zhang L, Zhang M, Zhang M, Zhang W, Zhang Y, Zhao C, Zhao Y, Zhou S, Zhou S, Zhu Q, Zou Y (2024) Deepseek llm: Scaling open-source language models with longtermism. arXiv:2401.02954"},{"key":"2216_CR57","unstructured":"Zeng A, Liu X, Du Z, Wang Z, Lai H, Ding M, Yang Z, Xu Y, Zheng W, Xia X, et al (2022) Glm-130b: an open bilingual pre-trained model. arXiv preprint arXiv:2210.02414"},{"key":"2216_CR58","doi-asserted-by":"crossref","unstructured":"Li Q, Cui L, Zhao X, Kong L, Bi W (2024) Gsm-plus: A comprehensive benchmark for evaluating the robustness of llms as mathematical problem solvers. arXiv preprint arXiv:2402.19255","DOI":"10.18653\/v1\/2024.acl-long.163"},{"key":"2216_CR59","doi-asserted-by":"crossref","unstructured":"Clark P, Tafjord O, Richardson K (2021) Transformers as soft reasoners over language. In: Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence, pp 3882\u20133890","DOI":"10.24963\/ijcai.2020\/537"},{"key":"2216_CR60","doi-asserted-by":"publisher","unstructured":"Dalvi B, Jansen P, Tafjord O, Xie Z, Smith H, Pipatanangkura L, Clark P (2021) Explaining answers with entailment trees. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp. 7358\u20137370. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.585. https:\/\/aclanthology.org\/2021.emnlp-main.585","DOI":"10.18653\/v1\/2021.emnlp-main.585"},{"key":"2216_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106237","volume":"204","author":"S Zhu","year":"2020","unstructured":"Zhu S, Cheng X, Su S (2020) Conversational semantic parsing over tables by decoupling and grouping actions. Knowledge-Based Syst 204:106237. https:\/\/doi.org\/10.1016\/j.knosys.2020.106237","journal-title":"Knowledge-Based Syst"},{"key":"2216_CR62","doi-asserted-by":"publisher","unstructured":"Chen Z, Chen W, Smiley C, Shah S, Borova I, Langdon D, Moussa R, Beane M, Huang T-H, Routledge B, Wang WY (2021) xinQA: a dataset of numerical reasoning over financial data. In: Proceedings of the 2021 conference on empirical methods in natural language processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, pp 3697\u20133711. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.300. https:\/\/aclanthology.org\/2021.emnlp-main.300","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"2216_CR63","doi-asserted-by":"publisher","unstructured":"Zhu F, Lei W, Huang Y, Wang C, Zhang S, Lv J, Feng F, Chua T-S (2021) TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. 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). Association for Computational Linguistics, pp 3277\u20133287. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.254. https:\/\/aclanthology.org\/2021.acl-long.254","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"2216_CR64","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110264","volume":"262","author":"B Qin","year":"2023","unstructured":"Qin B, Hui B, Wang L, Yang M, Li B, Huang F, Si L, Jiang Q, Li Y (2023) Schema dependency-enhanced curriculum pre-training for table semantic parsing. Knowl-Based Syst 262:110264. https:\/\/doi.org\/10.1016\/j.knosys.2023.110264","journal-title":"Knowl-Based Syst"},{"key":"2216_CR65","doi-asserted-by":"publisher","unstructured":"Li J, Wang R, Zhang N, Zhang W, Yang F, Chen H (2020) Logic-guided semantic representation learning for zero-shot relation classification. In: Proceedings of the 28th international conference on computational linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), pp 2967\u20132978. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.265. https:\/\/aclanthology.org\/2020.coling-main.265","DOI":"10.18653\/v1\/2020.coling-main.265"},{"key":"2216_CR66","doi-asserted-by":"publisher","unstructured":"Kaoudi Z, Manolescu I, Zampetakis S (2020) SPARQL query optimization for the cloud. Springer, Cham, pp 57\u201366. https:\/\/doi.org\/10.1007\/978-3-031-01875-6_5. https:\/\/doi.org\/10.1007\/978-3-031-01875-6_5","DOI":"10.1007\/978-3-031-01875-6_5"},{"key":"2216_CR67","doi-asserted-by":"publisher","unstructured":"Chen X, Zhang N, Xie X, Deng S, Yao Y, Tan C, Huang F, Si L, Chen H (2022) Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction. In: Proceedings of the ACM web conference 2022. WWW \u201922. Association for Computing Machinery, New York, NY, USA, pp 2778\u20132788. https:\/\/doi.org\/10.1145\/3485447.3511998","DOI":"10.1145\/3485447.3511998"},{"key":"2216_CR68","doi-asserted-by":"crossref","unstructured":"Duan L, Wang J, Luo B, Sun Q (2024) Simple knowledge graph completion model based on PU learning and prompt learning. Knowl Inf Syst 1\u201315","DOI":"10.1007\/s10115-023-02040-z"},{"key":"2216_CR69","doi-asserted-by":"crossref","unstructured":"Chen S, Chen Z, Sun H, Su Y (2023) Error detection for text-to-SQL semantic parsing. arXiv:2305.13683","DOI":"10.18653\/v1\/2023.findings-emnlp.785"},{"key":"2216_CR70","doi-asserted-by":"publisher","unstructured":"Zhang T, Liu C, Lee W-H, Su Y, Sun H (2023) Federated learning for semantic parsing: Task formulation, evaluation setup, new algorithms. In: Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Toronto, Canada, pp 12149\u201312163. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.678. https:\/\/aclanthology.org\/2023.acl-long.678","DOI":"10.18653\/v1\/2023.acl-long.678"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02216-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-024-02216-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02216-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T12:06:47Z","timestamp":1738325207000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-024-02216-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,6]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2216"],"URL":"https:\/\/doi.org\/10.1007\/s10115-024-02216-1","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2024,9,6]]},"assertion":[{"value":"16 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 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"}}]}}