Original title: Prompting for justice: generative AI, translanguaging, and the equity imperative in bilingual education
Generative AI tools often learn mostly from English-language material, which can affect how they respond to bilingual students. This paper proposes five principles for using prompts in ways that support fairness in bilingual classrooms. The principles cover how prompts are written, how answers are checked, how students take part, what role AI plays, and whose knowledge counts. The framework comes from a synthesis of existing theory and research, not a classroom trial.
Imagine a group cooking dinner where everyone brings recipes from home. Trouble starts when one person’s recipes are treated as the only proper ones, and the others are ignored or corrected. In this paper, the recipes stand for students’ languages and knowledge, while the five classroom principles guide teachers in using AI without letting its English-heavy habits decide whose contributions count.
Bilingual teachers and students are using generative AI before classroom guidance has caught up. This framework gives educators principles for shaping prompts and judging AI responses so that students’ languages and knowledge are not treated as secondary.
The abstract describes a theoretical framework developed by synthesizing 20 core sources. It does not report classroom testing, measured effects on student learning, or evidence that applying the principles reduces language bias in AI outputs.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Prompting for justice: generative AI, translanguaging, and the equity imperative in bilingual education — Kidega Charles — Cogent Education — doi:10.1080/2331186x.2026.2740865
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.