View in EDS

Linguistic Control in AI Text Generation: An Accessible Prompt-Based Approach Targeting L2 Spanish Absolute Beginners

Saved in:
Bibliographic Details
Title: Linguistic Control in AI Text Generation: An Accessible Prompt-Based Approach Targeting L2 Spanish Absolute Beginners
Language: English
Authors: Raúl Getino-Diez (ORCID 0009-0005-8862-8445), Mikel García-Madariaga (ORCID 0009-0009-4796-1224)
Source: Technology in Language Teaching & Learning. 2026 8.
Availability: Castledown Publishers. Ground Level, 470 St Kilda Road, Melbourne, 3004, Australia. Tel: +61-3-7003-8355; e-mail: contact@castledown.com; Web site: https://www.castledown.com/journals/tltl
Peer Reviewed: Y
Page Count: 21
Publication Date: 2026
Document Type: Journal Articles
Reports - Research
Descriptors: Second Language Learning, Spanish, Novices, Artificial Intelligence, Linguistics, Technology Uses in Education
ISSN: 2652-1687
Abstract: Generative artificial intelligence (AI) offers strong potential for developing customized second language learning materials and tools. However, generating texts for absolute beginners which require strict lexical and grammatical control remains a challenge. Although controlled text generation (CTG) techniques exist, they often require technical expertise and infrastructure, limiting accessibility for educators. This study evaluates, in the context of Spanish, a prompt-based approach that leverages large language models (LLMs) without fine-tuning or specialized tools. Prompts enforce linguistic constraints defined in two attachments: a categorized Spanish vocabulary list, and a set of example sentences illustrating approved Spanish grammatical structures organized by communicative function. Three variables were manipulated: "AI model" (ChatGPT-4o vs. Claude 3.5 Sonnet), "prompt type" (standard vs. extended, with constraint-enhancing techniques), and "attachment format" (rich-heavyweight vs. lightweight JSON). A secondary variable, "text type" (city descriptions, personal introductions, and dialogues), was also examined. A total of 720 texts were generated, 30 per condition. Measures included proportions of non-compliant lexical and grammatical items, user-perceived latency, and errors in vocabulary, grammar, and coherence. Model choice was the primary driver of constraint adherence, with Claude 3.5 Sonnet outperforming ChatGPT-4o. Extended prompts improved adherence across models. Attachment format showed no systematic effect on adherence, but JSON significantly reduced latency and response-time variability. Text type also influenced adherence, and error rates remained low. Findings offer educators a scalable, low-barrier solution for generating tailored beginner-level Spanish materials and AI-powered tools using LLMs, along with insights into how different design choices affect performance. This approach, transferable to other languages, provides a practical alternative to resource-intensive CTG techniques, addressing a critical gap in AI-assisted language education.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1501451
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1501451
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1501451
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Linguistic Control in AI Text Generation: An Accessible Prompt-Based Approach Targeting L2 Spanish Absolute Beginners
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Raúl+Getino-Diez%22">Raúl Getino-Diez</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0005-8862-8445">0009-0005-8862-8445</externalLink>)<br /><searchLink fieldCode="AR" term="%22Mikel+García-Madariaga%22">Mikel García-Madariaga</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0009-4796-1224">0009-0009-4796-1224</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Technology+in+Language+Teaching+%26+Learning%22"><i>Technology in Language Teaching & Learning</i></searchLink>. 2026 8.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Castledown Publishers. Ground Level, 470 St Kilda Road, Melbourne, 3004, Australia. Tel: +61-3-7003-8355; e-mail: contact@castledown.com; Web site: https://www.castledown.com/journals/tltl
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 21
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2026
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Second+Language+Learning%22">Second Language Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Spanish%22">Spanish</searchLink><br /><searchLink fieldCode="DE" term="%22Novices%22">Novices</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Linguistics%22">Linguistics</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2652-1687
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Generative artificial intelligence (AI) offers strong potential for developing customized second language learning materials and tools. However, generating texts for absolute beginners which require strict lexical and grammatical control remains a challenge. Although controlled text generation (CTG) techniques exist, they often require technical expertise and infrastructure, limiting accessibility for educators. This study evaluates, in the context of Spanish, a prompt-based approach that leverages large language models (LLMs) without fine-tuning or specialized tools. Prompts enforce linguistic constraints defined in two attachments: a categorized Spanish vocabulary list, and a set of example sentences illustrating approved Spanish grammatical structures organized by communicative function. Three variables were manipulated: "AI model" (ChatGPT-4o vs. Claude 3.5 Sonnet), "prompt type" (standard vs. extended, with constraint-enhancing techniques), and "attachment format" (rich-heavyweight vs. lightweight JSON). A secondary variable, "text type" (city descriptions, personal introductions, and dialogues), was also examined. A total of 720 texts were generated, 30 per condition. Measures included proportions of non-compliant lexical and grammatical items, user-perceived latency, and errors in vocabulary, grammar, and coherence. Model choice was the primary driver of constraint adherence, with Claude 3.5 Sonnet outperforming ChatGPT-4o. Extended prompts improved adherence across models. Attachment format showed no systematic effect on adherence, but JSON significantly reduced latency and response-time variability. Text type also influenced adherence, and error rates remained low. Findings offer educators a scalable, low-barrier solution for generating tailored beginner-level Spanish materials and AI-powered tools using LLMs, along with insights into how different design choices affect performance. This approach, transferable to other languages, provides a practical alternative to resource-intensive CTG techniques, addressing a critical gap in AI-assisted language education.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2026
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1501451
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1501451
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
    Subjects:
      – SubjectFull: Second Language Learning
        Type: general
      – SubjectFull: Spanish
        Type: general
      – SubjectFull: Novices
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Linguistics
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
    Titles:
      – TitleFull: Linguistic Control in AI Text Generation: An Accessible Prompt-Based Approach Targeting L2 Spanish Absolute Beginners
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Raúl Getino-Diez
      – PersonEntity:
          Name:
            NameFull: Mikel García-Madariaga
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 2652-1687
          Numbering:
            – Type: volume
              Value: 8
          Titles:
            – TitleFull: Technology in Language Teaching & Learning
              Type: main
ResultId 1