Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues

Autores
Parra, Verónica Ester; Corica, Ana Rosa; Godoy, Daniela Lis
Año de publicación
2026
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
AI-powered tutors that interact with students in question-answering scenarios using large language models (LLMs) as foundational models for generating responses represent a potential scalable solution to the growing demand for one-to-one tutoring. In fields like mathematics, where students often face difficulties, sometimes leading to frustration, easyto- use natural language interactions emerge as an alternative for enhancing engagement and providing personalized advice. Despite their promising potential, the challenges for LLM-based tutors in the math domain are twofold. First, the absence of genuine reasoning and generalization abilities in LLMs frequently results in mathematical errors, ranging from inaccurate calculations to flawed reasoning steps and even the appearance of contradictions.Second, the pedagogical capabilities of AI-powered tutors must be examined beyond simple question-answering scenarios since their effectiveness in math tutoring largely depends on their ability to guide students in building mathematical knowledge. In this paper, we present a study exploring the pedagogical aspects of LLM-based tutors through the analysis of their responses in math dialogues using feature extraction techniques applied to textual data. The use of natural language processing (NLP) techniques enables the quantification and characterization of several aspects of pedagogical strategies deployed in the answers, which the literature identifies as essential for engaging students and providing valuable guidance in mathematical problem-solving. The findings of this study have direct practical implications in the design of more effective math AI-powered tutors as they highlight the most salient characteristics of valuable responses and can thus inform the training of LLMs.
Fil: Parra, Verónica Ester. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires; . Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
Fil: Corica, Ana Rosa. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires;
Fil: Godoy, Daniela Lis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
Materia
AI TUTORS
LLMS
MATHEMATICS EDUCATION
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/289713
Acceder
id CONICETDig_8603f2d0978a2218d14693a5e1d7be78
oai_identifier_str oai:ri.conicet.gov.ar:11336/289713
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Insights on the Pedagogical Abilities of AI-Powered Tutors in Math DialoguesParra, Verónica EsterCorica, Ana RosaGodoy, Daniela LisAI TUTORSLLMSMATHEMATICS EDUCATIONhttps://purl.org/becyt/ford/5.3https://purl.org/becyt/ford/5AI-powered tutors that interact with students in question-answering scenarios using large language models (LLMs) as foundational models for generating responses represent a potential scalable solution to the growing demand for one-to-one tutoring. In fields like mathematics, where students often face difficulties, sometimes leading to frustration, easyto- use natural language interactions emerge as an alternative for enhancing engagement and providing personalized advice. Despite their promising potential, the challenges for LLM-based tutors in the math domain are twofold. First, the absence of genuine reasoning and generalization abilities in LLMs frequently results in mathematical errors, ranging from inaccurate calculations to flawed reasoning steps and even the appearance of contradictions.Second, the pedagogical capabilities of AI-powered tutors must be examined beyond simple question-answering scenarios since their effectiveness in math tutoring largely depends on their ability to guide students in building mathematical knowledge. In this paper, we present a study exploring the pedagogical aspects of LLM-based tutors through the analysis of their responses in math dialogues using feature extraction techniques applied to textual data. The use of natural language processing (NLP) techniques enables the quantification and characterization of several aspects of pedagogical strategies deployed in the answers, which the literature identifies as essential for engaging students and providing valuable guidance in mathematical problem-solving. The findings of this study have direct practical implications in the design of more effective math AI-powered tutors as they highlight the most salient characteristics of valuable responses and can thus inform the training of LLMs.Fil: Parra, Verónica Ester. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires; . Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; ArgentinaFil: Corica, Ana Rosa. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires;Fil: Godoy, Daniela Lis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; ArgentinaMDPI2026-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/289713Parra, Verónica Ester; Corica, Ana Rosa; Godoy, Daniela Lis; Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues; MDPI; Information; 17; 1; 1-2026; 1-212078-2489CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2078-2489/17/1/51info:eu-repo/semantics/altIdentifier/doi/10.3390/info17010051info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T15:02:27Zoai:ri.conicet.gov.ar:11336/289713instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-08-25 15:02:27.266CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
title Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
spellingShingle Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
Parra, Verónica Ester
AI TUTORS
LLMS
MATHEMATICS EDUCATION
title_short Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
title_full Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
title_fullStr Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
title_full_unstemmed Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
title_sort Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues
dc.creator.none.fl_str_mv Parra, Verónica Ester
Corica, Ana Rosa
Godoy, Daniela Lis
author Parra, Verónica Ester
author_facet Parra, Verónica Ester
Corica, Ana Rosa
Godoy, Daniela Lis
author_role author
author2 Corica, Ana Rosa
Godoy, Daniela Lis
author2_role author
author
dc.subject.none.fl_str_mv AI TUTORS
LLMS
MATHEMATICS EDUCATION
topic AI TUTORS
LLMS
MATHEMATICS EDUCATION
purl_subject.fl_str_mv https://purl.org/becyt/ford/5.3
https://purl.org/becyt/ford/5
dc.description.none.fl_txt_mv AI-powered tutors that interact with students in question-answering scenarios using large language models (LLMs) as foundational models for generating responses represent a potential scalable solution to the growing demand for one-to-one tutoring. In fields like mathematics, where students often face difficulties, sometimes leading to frustration, easyto- use natural language interactions emerge as an alternative for enhancing engagement and providing personalized advice. Despite their promising potential, the challenges for LLM-based tutors in the math domain are twofold. First, the absence of genuine reasoning and generalization abilities in LLMs frequently results in mathematical errors, ranging from inaccurate calculations to flawed reasoning steps and even the appearance of contradictions.Second, the pedagogical capabilities of AI-powered tutors must be examined beyond simple question-answering scenarios since their effectiveness in math tutoring largely depends on their ability to guide students in building mathematical knowledge. In this paper, we present a study exploring the pedagogical aspects of LLM-based tutors through the analysis of their responses in math dialogues using feature extraction techniques applied to textual data. The use of natural language processing (NLP) techniques enables the quantification and characterization of several aspects of pedagogical strategies deployed in the answers, which the literature identifies as essential for engaging students and providing valuable guidance in mathematical problem-solving. The findings of this study have direct practical implications in the design of more effective math AI-powered tutors as they highlight the most salient characteristics of valuable responses and can thus inform the training of LLMs.
Fil: Parra, Verónica Ester. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires; . Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
Fil: Corica, Ana Rosa. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina. Nucleo de Investigacion En Educacion Matematica (niem) ; Facultad de Ciencias Exactas ; Universidad Nacional del Centro de la Provincia de Buenos Aires;
Fil: Godoy, Daniela Lis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tandil. Instituto Superior de Ingeniería del Software. Universidad Nacional del Centro de la Provincia de Buenos Aires. Instituto Superior de Ingeniería del Software; Argentina
description AI-powered tutors that interact with students in question-answering scenarios using large language models (LLMs) as foundational models for generating responses represent a potential scalable solution to the growing demand for one-to-one tutoring. In fields like mathematics, where students often face difficulties, sometimes leading to frustration, easyto- use natural language interactions emerge as an alternative for enhancing engagement and providing personalized advice. Despite their promising potential, the challenges for LLM-based tutors in the math domain are twofold. First, the absence of genuine reasoning and generalization abilities in LLMs frequently results in mathematical errors, ranging from inaccurate calculations to flawed reasoning steps and even the appearance of contradictions.Second, the pedagogical capabilities of AI-powered tutors must be examined beyond simple question-answering scenarios since their effectiveness in math tutoring largely depends on their ability to guide students in building mathematical knowledge. In this paper, we present a study exploring the pedagogical aspects of LLM-based tutors through the analysis of their responses in math dialogues using feature extraction techniques applied to textual data. The use of natural language processing (NLP) techniques enables the quantification and characterization of several aspects of pedagogical strategies deployed in the answers, which the literature identifies as essential for engaging students and providing valuable guidance in mathematical problem-solving. The findings of this study have direct practical implications in the design of more effective math AI-powered tutors as they highlight the most salient characteristics of valuable responses and can thus inform the training of LLMs.
publishDate 2026
dc.date.none.fl_str_mv 2026-01
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/289713
Parra, Verónica Ester; Corica, Ana Rosa; Godoy, Daniela Lis; Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues; MDPI; Information; 17; 1; 1-2026; 1-21
2078-2489
CONICET Digital
CONICET
url http://hdl.handle.net/11336/289713
identifier_str_mv Parra, Verónica Ester; Corica, Ana Rosa; Godoy, Daniela Lis; Insights on the Pedagogical Abilities of AI-Powered Tutors in Math Dialogues; MDPI; Information; 17; 1; 1-2026; 1-21
2078-2489
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2078-2489/17/1/51
info:eu-repo/semantics/altIdentifier/doi/10.3390/info17010051
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1874775062122332160
score 13.24418

Publicaciones similares