Prompting a learning disability shifts feedback toward word- and sentence-level remediation, simplified vocabulary, and lowered expectations¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? For students identified as having a learning disability, generated feedback focused on word- and sentence-level remediation and relied on simplified vocabulary, positioning these students as needing simplification rather than substantive writing instruction. → Tan et al. 2026

Evidence¶

Tan et al. 2026¶

Mei Tan, Lena Phalen, and Dorottya Demszky. 2026. Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback. In LAK 2026: 16th International Learning Analytics and Knowledge Conference (LAK 2026). ACM, New York, NY, USA. doi:10.1145/3785022.3785113

q2 · i? · causal · r2

Lexical comparison of learning-disability-prompted versus baseline feedback for the same essays; Table 3 shows marked-condition words such as try, help, simpler, shorter, and inclusive pronouns (you, we, let's), against more nuanced evaluative language when no disability was specified. No effect size is printed.

"For students identified as having a learning disability, generated feedback focused on word- and sentence-level remediation and relied on simplified vocabulary."

Discussion¶

Learner Variables¶

• Learning Disabilities and Developmental Differences — moderator: an instructional effect differs with it

Related Claims¶

• Teacher expectation bias predicted Dutch secondary students' performance up to five years later, after controls for prior achievement, IQ and motivation, in one large correlational cohort study — the general claim this finding bears on, with the studies behind it
• Downward Bloom control is benchmark-dependent: repository-level tasks are easier to simplify than algorithmic puzzles — related
• Simplifying journal articles and providing glossaries of unfamiliar terms preceded the second-cycle improvement in proposal writing — related
• AI's key contribution in STEM education is intelligent scaffolding that lowers the threshold for understanding knowledge, driving a shift from knowledge transmission to capability development — related
• SPED-adaptive prompting shifts tutor behavior toward We-Do scaffolding, naturalistic language support, and participation-affirming feedback across three codebooks — related
• Prior meta-analytic and experimental evidence reports positive effects of linguistic simplification on learning outcomes, attributed by the review literature cited in this article — related
• Reaching the qualitative SOLO phase in GenAI interaction required repeated meta-level learner interventions, demanding the very self-regulatory skills the tool was expected to support — related
• The general and coder models deploy distinct lexical strategies when raising cognitive demand, and neither deploys simplification vocabulary downward — related