Improving the Validity of Automatically Generated Feedback via Reinforcement Learning

Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid esp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org
Hauptverfasser: Scarlatos, Alexander, Smith, Digory, Woodhead, Simon, Lan, Andrew
Format: Paper
Sprache:Englisch
Veröffentlicht: Ithaca Cornell University Library, arXiv.org 12.12.2024
Schlagworte:
ISSN:2331-8422
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other desirable features. In this work, we address both problems of automatically generating and evaluating feedback while considering both correctness and alignment. First, we propose a rubric for evaluating math feedback and show that GPT-4 is able to effectively use it to annotate human-written and LLM-generated feedback. Second, we propose a framework for feedback generation that optimizes both correctness and alignment using reinforcement learning (RL). Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO). We show that our methods significantly increase the correctness and alignment of generated feedback with Llama 2, an open-source LLM, qualitatively analyze our generation and evaluation systems using case studies, and outline several areas for future work.
AbstractList Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other desirable features. In this work, we address both problems of automatically generating and evaluating feedback while considering both correctness and alignment. First, we propose a rubric for evaluating math feedback and show that GPT-4 is able to effectively use it to annotate human-written and LLM-generated feedback. Second, we propose a framework for feedback generation that optimizes both correctness and alignment using reinforcement learning (RL). Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO). We show that our methods significantly increase the correctness and alignment of generated feedback with Llama 2, an open-source LLM, qualitatively analyze our generation and evaluation systems using case studies, and outline several areas for future work.
Author Scarlatos, Alexander
Woodhead, Simon
Lan, Andrew
Smith, Digory
Author_xml – sequence: 1
  givenname: Alexander
  surname: Scarlatos
  fullname: Scarlatos, Alexander
– sequence: 2
  givenname: Digory
  surname: Smith
  fullname: Smith, Digory
– sequence: 3
  givenname: Simon
  surname: Woodhead
  fullname: Woodhead, Simon
– sequence: 4
  givenname: Andrew
  surname: Lan
  fullname: Lan, Andrew
BookMark eNotj1FLwzAURoMoOOd-gG8BnzuTm2ZLHsdwc1AQZPo6bpNbzWxTbdPh_r0FffreznfODbuMbSTG7qSY50Zr8YDdTzjNIRdqLqQS-QWbgFIyMznANZv1_VEIAYslaK0m7HXXfHXtKcR3nj6Iv2EdfEhn3lZ8NaS2wRQc1vWZbylSh4k83xD5Et0nPwXkLxRi1XaOGoqJF4RdHFm37KrCuqfZ_07ZfvO4Xz9lxfN2t14VGWqwmbEWjKgQK196cFQCCJLeG28VeikcjEG6NE5pGJWdwrKyYiFQulIuwagpu__DjgnfA_XpcGyHLo6PB7Bqmeux26pfHg9Uiw
ContentType Paper
Copyright 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
DOI 10.48550/arxiv.2403.01304
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni Edition)
ProQuest Central UK/Ireland
ProQuest Central Essentials - QC
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central Korea
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 2331-8422
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FG
ABJCF
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FRJ
HCIFZ
L6V
M7S
M~E
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
ID FETCH-LOGICAL-a529-899280faafdbd2ceb220e1dd8d93ad10c28555b8c352002c3abf9060a1cb17283
IEDL.DBID BENPR
IngestDate Mon Jun 30 09:29:48 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a529-899280faafdbd2ceb220e1dd8d93ad10c28555b8c352002c3abf9060a1cb17283
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
OpenAccessLink https://www.proquest.com/docview/2937453319?pq-origsite=%requestingapplication%
PQID 2937453319
PQPubID 2050157
ParticipantIDs proquest_journals_2937453319
PublicationCentury 2000
PublicationDate 20241212
PublicationDateYYYYMMDD 2024-12-12
PublicationDate_xml – month: 12
  year: 2024
  text: 20241212
  day: 12
PublicationDecade 2020
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2024
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 1.8924478
SecondaryResourceType preprint
Snippet Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Alignment
Annotations
Data augmentation
Distance learning
Error analysis
Feedback
Large language models
Machine learning
Tutoring
Title Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
URI https://www.proquest.com/docview/2937453319
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ3LT8JAEMY3Cpp48h0fSPbgtdDdbkv3ZNRANFHSIBo8kX0aIqHYAtH_3tlS8GDixWPTSzNtZ377zeQbhC4FMVIBV3s-s5HHVCg8bin34OuxNALCD5c-sw-tbjceDHhSCm55OVa5yolFotapchp5E8pSiwGbEH41_fDc1ijXXS1XaGyiqnMqYxVUvWl3k95aZaFRC5g5WLYzC_Oupsg-R4uGs6FruK4d-5WEi8rS2f3vM-2haiKmJttHG2ZygLaLiU6VH6LntVyAgfHwC_C2BuLGqcXX81laOLWK8fgLL42nATxxByqZFOodL0YC90zhqaoK-RCXNqxvR6jfafdv77xyh4InQgg5nKZo7FshrJaaKjhGU98QrWPNA6GJryjEJJSxCpz9ElWBkJb7kS-Ikm5zVXCMKpN0Yk4Q5lZFTMdc-UIy5ztoCAXeYzwOLYm5PEW1VZCG5X-QD38idPb37XO0QwEX3KAIoTVUmWVzc4G21GI2yrN6-VrrbjLzCa6S-8fk9RsJcrAs
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT8JAEJ4gavTkOz5Q96DHSrt9sHswxqgEwiPEoNET2e7DEAkgBZQf5X90tjw8mHjz4LlJ0-1MZ75vZvoNwJnwdCwRVztuYCInkKFwuKHcQe8xNEKEH051ZquFep09PfFGBj7n_8LYscp5TEwDtepJWyPPY1oqBIhNPH7Vf3Ps1ijbXZ2v0Ji6RUVP3pGyJZflW7TvOaXFu-ZNyZltFXBEiA-B_IIy1whhVKyoRGJJXe0pxRT3hfJcSVkYhjGTvhUkotIXseFu5ApPxnaXk4-3XYLlAH2dZWG5Ua41nhdFHRoVEKL70-5pqhWWF4OP9vjCqt5d2CZh8CPmp4msuPHPXsEmHl309WALMrq7DavpvKpMduBhUQwhiGDJI7IJhXyC9Ay5Hg17qQ6t6HQmZCqrjbCaFDFPx0K-knFbkHudKsbKtDhKZiKzL7vQ_IuD7EG22-vqfSDcyChQjEtXxIFVVdQeRTQbcBYaj_H4AHJzm7RmX3nS-jbI4e-XT2Gt1KxVW9VyvXIE6xSBkR2J8WgOssPBSB_DihwP28ngZOZRBFp_bMAv3skJxA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Improving+the+Validity+of+Automatically+Generated+Feedback+via+Reinforcement+Learning&rft.jtitle=arXiv.org&rft.au=Scarlatos%2C+Alexander&rft.au=Smith%2C+Digory&rft.au=Woodhead%2C+Simon&rft.au=Lan%2C+Andrew&rft.date=2024-12-12&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2403.01304