Style over Story: Measuring LLM Narrative Preferences via Structured Selection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jung, Donghoon, Choi, Jiwoo, Chae, Songeun, Jung, Seohyon
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917421528383488
author Jung, Donghoon
Choi, Jiwoo
Chae, Songeun
Jung, Seohyon
author_facet Jung, Donghoon
Choi, Jiwoo
Chae, Songeun
Jung, Seohyon
contents We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers an interpretable lens on LLMs' narrative selection behavior. We developed a library of 200 narratology-grounded constraints and prompted selections from six LLMs under three different instruction types: basic, quality-focused, and creativity-focused. Findings demonstrate that models consistently prioritize Style over narrative content elements like Event, Character, and Setting. Style preferences remain stable across models and instruction types, whereas content elements show cross-model divergence and instructional sensitivity. These results suggest that LLMs have latent narrative preferences, which should inform how the NLP community evaluates and deploys models in creative domains.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02025
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Style over Story: Measuring LLM Narrative Preferences via Structured Selection
Jung, Donghoon
Choi, Jiwoo
Chae, Songeun
Jung, Seohyon
Computation and Language
We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers an interpretable lens on LLMs' narrative selection behavior. We developed a library of 200 narratology-grounded constraints and prompted selections from six LLMs under three different instruction types: basic, quality-focused, and creativity-focused. Findings demonstrate that models consistently prioritize Style over narrative content elements like Event, Character, and Setting. Style preferences remain stable across models and instruction types, whereas content elements show cross-model divergence and instructional sensitivity. These results suggest that LLMs have latent narrative preferences, which should inform how the NLP community evaluates and deploys models in creative domains.
title Style over Story: Measuring LLM Narrative Preferences via Structured Selection
topic Computation and Language
url https://arxiv.org/abs/2510.02025