Claims

Prompts referencing architectural styles or local architectures yielded less desired image outcomes than future-themed prompts, motivating selectable checkpoints in GAI-A

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q2 i? Images aligning with future-themed prompts resembled science-fiction stage sets and yielded more favorable results, while prompts referencing architectural styles or local architectures did not yield the same desired outcomes. → Leman Figen Gül 2025

Evidence

Leman Figen Gül 2025

Leman Figen Gül, Burak Delikanlı, Oğulcan Üneşi, Ertuğrul Ömer Gül. (2025). Development and applications of Generative AI in architectural design studios. ITU A|Z • Vol 22 No 3 • November 2025 • 751-774. https://doi.org/10.58278/0.2025.109

q2 · i? · design · r2

Based on the authors' discussions and observations of students' outcomes in the studios, comparing two prompt types. The article reports the contrast descriptively from student outputs; no statistical test or effect size is printed.

"the images that align more closely with the prompts focused on the theme of the future, resembling stage-like creations seen in science fiction movie sets, yield more favorable results. In contrast, the prompts that reference architectural styles or local architectures don't yield the same desired outcomes."

Discussion

Page metadata
Field Value
type claim
id style-prompts-underperform-future-themed-prompts
title Prompts referencing architectural styles or local architectures yielded less desired image outcomes than future-themed prompts, motivating selectable checkpoints in GAI-A
description Prompts referencing architectural styles or local architectures yielded less desired image outcomes than future-themed prompts, motivating selectable checkpoints in GAI-A
status review
evidence_strength weak
newest_evidence 2025
generated by process:wiki-ingest on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — leman-figen-gül-2025

Frontmatter is the page's machine-readable record — see the Schema & Guide.