arXiv:2606. 17350v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet the question of whether these models are capable of generating diverse outputs remains contested.
By Thennal DK, Hans Ole Hatzel
The paper investigates how characters in large language model (LLM)-generated stories compare to those in human-written stories. Using narratological definitions, it analyzes eight complex character dimensions—including stylization and wholeness—to automatically categorize characters in both LLM and human texts. The study then contrasts these categories to answer whether LLMs produce similar and varied character portrayals as human authors.
By Anneliese Brei, Abhisheik Sharma, Nicholas Sanaie, Lu Wang, Snigdha Chaturvedi
The paper investigates how Large Language Models (LLMs) construct fictional worlds, specifically examining setting as a measurable aspect of storyworld creation. By generating 1,000 AI stories per model in English and German and comparing them to human-authored fiction from Project Gutenberg, the authors classify narrative space into five categories—action, perceived, visual, descriptive, and no space—using fine‑tuned BERT classifiers. Results show that human texts mainly use action space, grounding narratives in character-environment interaction, while LLMs consistently overproduce perceived space, focusing on atmosphere and affect, with this pattern varying by model and language.
By Katrin Rohrbacher, Bj\"orn Nieth, Emmanuelle Salin, Bjoern Eskofier, Michaela Mahlberg
arXiv:2605. 17064v2 Announce Type: replace Abstract: Large language models are optimized for instruction following and agentic tasks remain poorly aligned with the requirements of high-quality creative writing.
By Jan Zierstek, Matteo Batelic, Maya Medjad, Tim Sch\"onenberger
The paper introduces VOLM, a framework that quantifies how much original value a human adds to a document beyond what a language model could generate from a task description alone. Unlike existing tools that focus on stylistic detection, VOLM extracts content at varying granularities, reconstructs it with an LLM, and compares these reconstructions to those derived from the task description. Evaluations across news articles, ICLR peer reviews, and argumentative essays show that VOLM can distinguish human-authored texts from LLM-generated ones while remaining robust to content-preserving transformations.
By Vibhhu Sharma, Thorsten Joachims, Sarah Dean
Evaluating creativity in large language model (LLM) outputs remains challenging because creativity is multidimensional and human-centered. We examine how reliably LLMs evaluate short literary text in...