PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 21, 2026Frontiers in Education2 citationsOpen Access

Using AI to adapt reading input for mixed-proficiency EFL learners

HAHesham AldamenAAAreen AlnemratMAMutasim Al‐Deaibes

Key Points

  • To determine whether AI-driven text adaptation improves reading comprehension across different proficiency levels in mixed-ability English as a foreign language (EFL) classrooms.
  • Assessed 48 university EFL students categorized into Intermediate-Low and Advanced-Low proficiencies based on ACTFL guidelines.
  • Used a 2 × 2 mixed factorial design to evaluate inference-making and specific-information retrieval on original versus AI-adapted texts.
  • Counterbalanced text presentation order across participants using two parallel test forms to mitigate sequence effects.
  • Intermediate-Low learners scored significantly higher on AI-adapted texts than on original texts (p < .001).
  • Advanced-Low learners demonstrated comparable performance across original and adapted text versions.
  • Identified a significant text-by-proficiency interaction effect (p < .001), indicating lower-proficiency learners benefit without disadvantaging advanced learners.

Abstract

Mixed-proficiency EFL classrooms complicate the provision of level-appropriate reading input. This study examined whether AI-based text adaptation improves reading comprehension for learners at different proficiency levels. Grounded in Krashen's Input Hypothesis and Cognitive Load Theory, the study used a 2 × 2 mixed factorial design (text version: original vs. AI-adapted; proficiency: Intermediate-Low vs. Advanced-Low) to test performance on inference-making and reading-for-specific-information tasks. Forty-eight university EFL students, classified using ACTFL guidelines, completed comprehension tasks using original and AI-adapted versions of the same source texts, with text-version order counterbalanced using two parallel test forms to reduce order effects. Intermediate-Low learners scored significantly higher on adapted than on original texts ( p .001), whereas Advanced-Low learners showed comparable performance across versions. A significant text-by-proficiency interaction ( p .001) suggests that AI-assisted adaptation can support differentiated reading instruction by improving access to comprehensible input for lower-proficiency learners without disadvantaging higher-proficiency learners, while providing a transparent workflow for proficiency-aligned adaptation.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Aldamen et al. (2026) studied this question.

synapsesocial.com/papers/6a08bd359a6c4ba6e610d6bchttps://doi.org/10.3389/feduc.2026.1737903
Ask AI
Helpful
Bookmark
Share
View Full Paper