Abstract:Large Language Models (LLMs) are increasingly used to generate pictures, texts, music, videos, and other works that have traditionally required human creativity. LLM-generated artifacts are often rated better than human-generated works in controlled studies. At the same time, they can come across as generic and hollow. We propose to resolve this tension by arguing that LLMs systematically generate kitsch, and that this is a consequence of the way in which they are trained. We also show empirically that readers perceive LLM-generated stories as kitschier, if we control for their definition of "kitsch". We discuss implications for the design of future studies and for creative tasks such as research and coding.
| Comments: | submitted to EMNLP 26 |
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7; J.5 |
| Cite as: | arXiv:2604.25929 [cs.CL] |
| (or arXiv:2604.25929v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.25929 arXiv-issued DOI via DataCite |
Submission history
From: Xenia Klinge [view email]
[v1]
Wed, 1 Apr 2026 16:13:09 UTC (344 KB)