File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: HAROR: A System for Highlighting and Rephrasing Open-Ended Responses

TitleHAROR: A System for Highlighting and Rephrasing Open-Ended Responses
Authors
Lin, JionghaoKoedinger, Kenneth R.
Keywordsfeedback
generative artificial intelligence
large language models
natural language processing
Issue Date2024
Citation
L@S 2024 - Proceedings of the 11th ACM Conference on Learning @ Scale, 2024, p. 553-555 How to Cite?
DOI: http://dx.doi.org/10.1145/3657604.3664721
AbstractAutomated feedback systems are pivotal for scaling personalized learning, especially when dealing with large cohorts of learners. This paper introduces HAROR (Highlighting and Rephrasing Open-ended Responses), a feedback system that utilizes the advanced capabilities of Generative Pre-trained Transformer (GPT) models, including GPT-4 and GPT-3.5, to provide explanatory feedback on learner responses (trainee tutors as learners in our study) to open-ended questions. HAROR can identify desirable and undesirable parts of open-ended responses, offer explanatory feedback, and rephrase the undesired responses into desirable forms, aiming to foster learners' understanding and improvement.
Persistent Identifierhttp://hdl.handle.net/10722/354348

 

DC FieldValueLanguage
dc.contributor.authorLin, Jionghao-
dc.contributor.authorKoedinger, Kenneth R.-
dc.date.accessioned2025-02-07T08:48:02Z-
dc.date.available2025-02-07T08:48:02Z-
dc.date.issued2024-
dc.identifier.citationL@S 2024 - Proceedings of the 11th ACM Conference on Learning @ Scale, 2024, p. 553-555-
dc.identifier.urihttp://hdl.handle.net/10722/354348-
dc.description.abstractAutomated feedback systems are pivotal for scaling personalized learning, especially when dealing with large cohorts of learners. This paper introduces HAROR (Highlighting and Rephrasing Open-ended Responses), a feedback system that utilizes the advanced capabilities of Generative Pre-trained Transformer (GPT) models, including GPT-4 and GPT-3.5, to provide explanatory feedback on learner responses (trainee tutors as learners in our study) to open-ended questions. HAROR can identify desirable and undesirable parts of open-ended responses, offer explanatory feedback, and rephrase the undesired responses into desirable forms, aiming to foster learners' understanding and improvement.-
dc.languageeng-
dc.relation.ispartofL@S 2024 - Proceedings of the 11th ACM Conference on Learning @ Scale-
dc.subjectfeedback-
dc.subjectgenerative artificial intelligence-
dc.subjectlarge language models-
dc.subjectnatural language processing-
dc.titleHAROR: A System for Highlighting and Rephrasing Open-Ended Responses-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/3657604.3664721-
dc.identifier.scopuseid_2-s2.0-85199920840-
dc.identifier.spage553-
dc.identifier.epage555-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats