View in EDS

ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation

Saved in:
Bibliographic Details
Title: ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation
Language: English
Authors: Andreea Dutulescu, Stefan Ruseti (ORCID 0000-0002-0380-6814), Mihai Dascalu (ORCID 0000-0002-4815-9227), Danielle S. McNamara (ORCID 0000-0001-5869-1420)
Source: Grantee Submission. 2026.
Peer Reviewed: Y
Page Count: 13
Publication Date: 2026
Sponsoring Agency: National Center for Education Research (NCER) (ED/IES)
Contract Number: R305T240035
Document Type: Speeches/Meeting Papers
Reports - Research
Descriptors: Automation, Questioning Techniques, Artificial Intelligence, Technology Uses in Education, Models
Abstract: Question generation plays an important role in educational applications, enabling automated assessment and reading comprehension support. Attribute-controlled question generation aims to produce questions that fit predefined characteristics such as difficulty, focus, or coverage. Existing methods predominantly rely on supervised fine-tuning, which often fails to impose a strong adherence to attribute values, resulting in weak coupling between prompt specifications and model outputs. We introduce Odds-Ratio Steerable Optimization (ORSO), a framework designed to enhance attribute sensitivity in question generation models. Building upon preference-based learning techniques without requiring human-curated preference sets, ORSO uses input-level perturbations to create contrastive training signals. Empirical evaluations on both exhaustive and expert-validated attribute configurations indicate that ORSO performs better than SteerLM and ORPO methods in enforcing attribute conformity while maintaining output quality. These results argue for the benefits of explicit attribute-aware optimization in controllable question generation tasks. [This paper was published in: "Findings of the Association for Computational Linguistics: EACL 2026," Association for Computational Linguistics, 2026, pp. 5248-5259.]
Abstractor: As Provided
IES Funded: Yes
Entry Date: 2026
Access URL: https://aclanthology.org/2026.findings-eacl.277/
Accession Number: ED679868
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: ED679868
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Andreea+Dutulescu%22">Andreea Dutulescu</searchLink><br /><searchLink fieldCode="AR" term="%22Stefan+Ruseti%22">Stefan Ruseti</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-0380-6814">0000-0002-0380-6814</externalLink>)<br /><searchLink fieldCode="AR" term="%22Mihai+Dascalu%22">Mihai Dascalu</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-4815-9227">0000-0002-4815-9227</externalLink>)<br /><searchLink fieldCode="AR" term="%22Danielle+S%2E+McNamara%22">Danielle S. McNamara</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-5869-1420">0000-0001-5869-1420</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Grantee+Submission%22"><i>Grantee Submission</i></searchLink>. 2026.
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 13
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2026
– Name: SourceSuprt
  Label: Sponsoring Agency
  Group: SrcSuprt
  Data: National Center for Education Research (NCER) (ED/IES)
– Name: NumberContract
  Label: Contract Number
  Group: NumCntrct
  Data: R305T240035
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Speeches/Meeting Papers<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Automation%22">Automation</searchLink><br /><searchLink fieldCode="DE" term="%22Questioning+Techniques%22">Questioning Techniques</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Models%22">Models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Question generation plays an important role in educational applications, enabling automated assessment and reading comprehension support. Attribute-controlled question generation aims to produce questions that fit predefined characteristics such as difficulty, focus, or coverage. Existing methods predominantly rely on supervised fine-tuning, which often fails to impose a strong adherence to attribute values, resulting in weak coupling between prompt specifications and model outputs. We introduce Odds-Ratio Steerable Optimization (ORSO), a framework designed to enhance attribute sensitivity in question generation models. Building upon preference-based learning techniques without requiring human-curated preference sets, ORSO uses input-level perturbations to create contrastive training signals. Empirical evaluations on both exhaustive and expert-validated attribute configurations indicate that ORSO performs better than SteerLM and ORPO methods in enforcing attribute conformity while maintaining output quality. These results argue for the benefits of explicit attribute-aware optimization in controllable question generation tasks. [This paper was published in: "Findings of the Association for Computational Linguistics: EACL 2026," Association for Computational Linguistics, 2026, pp. 5248-5259.]
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: CodeSource
  Label: IES Funded
  Group: SrcInfo
  Data: Yes
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2026
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://aclanthology.org/2026.findings-eacl.277/" linkWindow="_blank">https://aclanthology.org/2026.findings-eacl.277/</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED679868
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED679868
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
    Subjects:
      – SubjectFull: Automation
        Type: general
      – SubjectFull: Questioning Techniques
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Models
        Type: general
    Titles:
      – TitleFull: ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Andreea Dutulescu
      – PersonEntity:
          Name:
            NameFull: Stefan Ruseti
      – PersonEntity:
          Name:
            NameFull: Mihai Dascalu
      – PersonEntity:
          Name:
            NameFull: Danielle S. McNamara
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Titles:
            – TitleFull: Grantee Submission
              Type: main
ResultId 1