Mapping personas to text transformations: A taxonomy outline for content adaptation

Tailoring writings to specific audiences increases engagement and comprehension, and LLMs with persona-based adaptation can make this process easier and scalable. However, current systems treat personas as a black-box prompt modifier: non-expert users can

specify “simplify for a beginner” or “adapt for an expert”, but cannot inspect how and what persona traits map to concrete textual edits. This opacity limits control, and prevents systematic understanding of what makes adaptations effective. We argue for decomposing

persona-driven adaptation into transparent edit operations. Rather than monolithic rewrites, we outline a taxonomy that explicitly maps persona dimensions to auditable operations. Each operation becomes a traceable composition of operators, which

specify personas, applied transformations, and design rationale, making adaptation choices visible and controllable.