Metraipolis › archive › dc_ae798cd4ceeb

Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation — arXiv:2609.05423

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.05423
License (as archived): CC0-1.0
Archived: 2026-10-16T12:49:37.213Z
SHA-256 of the archived text: 4d36bb5f9bd0e368958b78565a0bfc012af8c1c190774dcca4b7b017b8e10c3f
Stable URL of this page: https://metraipolis.com/documento/dc_ae798cd4ceeb

How to cite

Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation — arXiv:2609.05423 — arXiv (en), https://arxiv.org/abs/2609.05423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae798cd4ceeb (Metraipolis archive dc_ae798cd4ceeb, sha256 4d36bb5f9bd0e368958b78565a0bfc012af8c1c190774dcca4b7b017b8e10c3f)

BibTeX

@misc{dcae798cd4ceeb,
  title = {Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation — arXiv:2609.05423},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05423},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae798cd4ceeb; sha256 4d36bb5f9bd0e368958b78565a0bfc012af8c1c190774dcca4b7b017b8e10c3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evaluating mobile user interface quality at scale remains a persistent challenge in software engineering and human-computer interaction. Rule-based heuristic methods offer structural reliability but demand significant engineering effort, while human annotation does not scale to the volume of applications produced annually. Large language models present a promising alternative, yet their reliability for structured UI judgment has not been systematically examined, and the patterns behind their failures remain insufficiently characterized. This paper addresses both gaps. We begin with the complete RICO dataset of 66,261 real-world mobile application screens, from which we derive a refined evaluation corpus of 15,000 screens through a rigorous, literature-guided selection process. Each screen is assessed across seven criteria: structural JSON validity, minimum visible element count, clickable component presence, non-zero layout bounds, image integrity, and perceptual duplicate removal. Against this corpus, we apply a heuristic baseline built from severity-weighted usability signals, normalized layout metrics, and pixel-ratio complexity measures calibrated to real user sentiment. Multiple language models independently rate each screen across usability, layout quality, and visual complexity from structured JSON descriptions and raw screenshots. Dimension-level comparison against the heuristic uses agreement rates, Cohen's Kappa, and confidence calibration. Recurring divergence patterns are organized into a failure taxonomy and interpreted through transformer architectural signatures: MLE plausibility bias, attention misgrounding, and autoregressive over-commitment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computation and Language (cs.CL); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.05423 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T12:30:25.223Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).