2026-08-27T05:20:56Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/109002025-09-30T00:05:32Zcom_10259_4219com_10259_5086com_10259_2604col_10259_7349

Arnau-González, Pablo Serrano Mamolar, Ana Katsigiannis, Stamos Arevalillo-Herráez, Miguel 2025-09-29T10:33:37Z 2025-09-29T10:33:37Z 2023-06-30 978-3-031-36336-8 978-3-031-36335-1 https://hdl.handle.net/10259/10900 10.1007/978-3-031-36336-8_99 Math Word Problem (MWP) solving for teaching math with Intelligent Tutoring Systems (ITSs) faces a major limitation: ITSs only supervise pre-registered problems, requiring substantial manual effort to add new ones. ITSs cannot assist with student-generated problems. To address this, we propose an automated approach to translate MWPs to an ITS’s internal representation using pre-trained language models to convert MWP to Python code, which can then be imported easily. Experimental evaluation using various code models demonstrates our approach’s accuracy and potential for improvement. eng info:eu-repo/semantics/openAccess Math word problems Algebra tutoring Intelligent tutoring systems Automatic code generation Towards Automatic Tutoring of Custom Student-Stated Math Word Problems info:eu-repo/semantics/conferenceObject