From Unified to Differentiated Materials: Generative AI–Supported Adaptation of EAP Reading Materials

Synthesis: Gao (2026) examined whether generative-AI-supported adaptation of English for Academic Purposes (EAP) reading materials chiefly changes passage-level structural complexity or text-embedded functional support. Using a role-prompted workflow (barrier analysis, adaptation, fidelity checking, validation) and a 3×3 between-subjects design (N=135; proficiency × material condition), the study found that GenAI-supported differentiation operates primarily at the level of proficiency-specific support-layer design — glosses, sentence unpacking, rhetorical cues, claim-evidence notes, and critical prompts — rather than broad changes in passage-level structural complexity. Differentiated-AI materials most strongly outperformed unified-AI versions among high-proficiency learners (d = 1.40), with a moderate advantage among low-proficiency learners (d = 0.60) and a small difference for intermediate learners.

Key Findings

Study Design & Method

The study deployed a four-module role-prompted GenAI workflow — barrier analysis, adaptation, academic-fidelity checking, and validation — designed to make generation auditable and protect the source text's disciplinary meaning. A 3×3 between-subjects experiment (N = 135; n = 15 per cell) crossed proficiency level (low, intermediate, high) with material condition (original, unified-AI, differentiated-AI). Three EAP instructors evaluated 15 anonymized material versions. Analyses included automated structural-complexity indicators, leave-one-out discriminant analysis, within-proficiency planned contrasts (comparing differentiated-AI with unified-AI while holding proficiency constant), and omnibus outcome models. Learner-outcome analysis gave priority to within-stratum planned contrasts as the cleaner evidence, while the omnibus Proficiency × Material model described heterogeneity across strata.

Implications for AI in Education

The findings argue that GenAI's value for Language Learning materials lies not in blanket simplification but in targeted, proficiency-sensitive support-layer design that preserves academic fidelity — terminology, stance, hedging, citation relations, and argumentative structure. This reframes GenAI as a tool for differentiation where the key design decision is what support each proficiency level needs (lexical/syntactic access for low-proficiency readers, discourse organization for intermediate readers, stance/evidence evaluation for high-proficiency readers) rather than a single harder-or-easier rewrite. For teachers, the study offers a concrete, auditable role-prompted workflow for generating and validating materials, and it underscores the continued necessity of teacher oversight against hallucinated content, flattened stance, and over-simplification in Generative AI output.

Limitations

The learner-outcome and process indicators were collected in the same session, making the process estimates descriptive rather than causal. Immediate unsupported application did not differ by condition, limiting evidence on transfer. The expert-rating rubric and the specific EAP genre constrain generalization to other disciplines and material types. Sample sizes per cell (n = 15) are modest, and the within-proficiency comparisons, while cleaner, rest on single-instructor-generated material versions.

Connected Concepts

Connected Articles

Citation

Gao, X. (2026). From unified to differentiated materials: Generative AI–supported adaptation of EAP reading materials.