Cognitive Load-Informed Attention Budgets Across Self-Attention and Token–Context Attention
Mathematics · 06.11.2026 · 14 (21) · 4076
DOI: 10.3390/math14214076 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 06.11.2026. Verfasst von Jarrod Graham und 1 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We investigate a theory-informed attention framework combining Cognitive Load Theory (CLT)-inspired resource regulation with Token–Context Attention (TCA) and a TCA-specific application of root-mean-square (RMS) branch normalization. Seven primary conditions were evaluated across SNLI, SST-2, IMDb, AG News, and DBPedia 14 using 10 paired seeds and locked data manifests, with a validation-calibrated fixed-gate control for adaptive TCA-RMS. A separately locked secondary ablation added entropy-only CLT (CLT-E) to self-attention, TCA, and TCA-RMS under the same records and seeds. RMS branch normalization increased mean raw-TCA accuracy on all five datasets, with Holm-adjusted raw-TCA accuracy support on IMDb and AG News. In contrast, none of the prespecified direct mixed-CLT accuracy additions survived the within-dataset Holm correction; CLT-related evidence was localized to particular architectures, datasets, and metrics. No adaptive-versus-fixed accuracy contrast was detected after correction, and the entropy-only ablation shows that useful attenuation can arise without the full entropy–uncertainty–IDF composition. Accordingly, the results support branch-scale normalization and bounded attention-output gating as separable architectural interventions, while neither universal accuracy improvement nor human cognitive-load construct validity is claimed. These conclusions are restricted to lightweight, from-scratch classifiers trained under locked limited-data protocols; whether pretrained encoders change the need for TCA branch normalization or the effects of the CLT-inspired gate remains an open empirical question.
Zitieren
APA
Graham, J., & Sheng, V. S. (2026). Cognitive Load-Informed Attention Budgets Across Self-Attention and Token–Context Attention. Mathematics, 14(21), 4076. https://doi.org/10.3390/math14214076
Vancouver
Graham J, Sheng VS. Cognitive Load-Informed Attention Budgets Across Self-Attention and Token–Context Attention. Mathematics. 2026;14(21):4076. doi:10.3390/math14214076
BibTeX
@article{Graham2026,
author = {Graham, Jarrod and Sheng, Victor S.},
title = {Cognitive Load-Informed Attention Budgets Across Self-Attention and Token–Context Attention},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {21},
pages = {4076},
doi = {10.3390/math14214076}
}
EUVIMED