Saved in:
Bibliographic Details
Main Authors: Klinge, Xenia, Ortlieb, Stefan, Koller, Alexander
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.25929
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915965350969344
author Klinge, Xenia
Ortlieb, Stefan
Koller, Alexander
author_facet Klinge, Xenia
Ortlieb, Stefan
Koller, Alexander
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25929
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLMs Generate Kitsch
Klinge, Xenia
Ortlieb, Stefan
Koller, Alexander
Computation and Language
I.2.7; J.5
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.
title LLMs Generate Kitsch
topic Computation and Language
I.2.7; J.5
url https://arxiv.org/abs/2604.25929