Structures of Signs without Cultural Knowledge. Narrative Competence and Cultural Specificity in AI-Generated Fiction Lutostański, Bartosz article article article Text https://doi.org/10.25926/c5vp-bm59 https://nbn-resolving.org/urn:nbn:de:hbz:468-20261008-114141-5 https://elpub.bib.uni-wuppertal.de/receive/ https://elpub.bib.uni-wuppertal.de/receive/duepublico_mods_00000883 doc-type:article ScholarlyArticle ddc:800 0820 Allgemeine und vergleichende Literaturwissenschaft Fakultät für Geistes- und Kulturwissenschaften » DIEGESIS » Jg. 15 (2026) H. 1 This article argues that narrative competence and cultural competence are independent variables in AI-generated fiction: a text can be mimetically vivid, synthetically controlled, and thematically coherent while getting its cultural and historical substance precisely wrong. To demonstrate this, it compares two systems – ChatGPT, a globally trained commercial model, and PLLUM, a Polish academic model – across a corpus of ten prompts requiring short stories set in post-1939 Polish contexts, with the culturally decisive reference embedded in the situation rather than stated. The method combines two instruments applied in sequence: James Phelan’s tripartite (mimetic, synthetic, thematic) model, adapted posthumanistically to treat AI outputs as “structures of signs” rather than rhetorical acts; and a cultural competence rubric assessing factual accuracy, nuance, contested material, and depth of embedding. Two case studies – a 1967 Krak.w scene and a contemporary scene turning on the rapper Mata’s Patointeligencja – yield a typology of four failure modes: Generic Approximation, Emotional Inversion, Content Substitution, and Perspectival Misreading. The discussion proposes a distinction between cultural familiarity and historical situatedness, and argues that the transparency asymmetry between academic and commercial AI is constitutive of the question of whose cultural knowledge these systems encode. eng Diegesis -- 2195-2116 all rights reserved info:eu-repo/semantics/restrictedAccess