Looking for the inner music : Probing LLMs’ understanding of literary style
Computational Humanities Research · 2025
DOI: 10.1017/chr.2025.10003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Humanities Research, 2025. Verfasst von Rebecca M. M. Hicke und 1 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Language models have the ability to identify the characteristics of much shorter literary passages than was thought feasible with traditional stylometry. We evaluate authorship and genre detection for a new corpus of literary novels. We find that a range of LLMs are able to distinguish authorship and genre, but that different models do so in different ways. Some models rely more on memorization, while others make greater use of author or genre characteristics learned during fine-tuning. We additionally use three methods – direct syntactic ablation of input text and two means of studying internal model values – to probe one high-performing LLM for features that characterize styles. We find that authorial style is easier to characterize than genre-level style and is more impacted by minor syntactic decisions and contextual word usage. However, some traits like pronoun usage and word order prove significant for defining both kinds of literary style.
Zitieren
APA
Hicke, R. M. M., & Mimno, D. (2025). Looking for the inner music : Probing LLMs’ understanding of literary style. Computational Humanities Research. https://doi.org/10.1017/chr.2025.10003
Vancouver
Hicke RMM, Mimno D. Looking for the inner music : Probing LLMs’ understanding of literary style. Computational Humanities Research. 2025. doi:10.1017/chr.2025.10003
BibTeX
@article{Hicke2025,
author = {Hicke, Rebecca M. M. and Mimno, David},
title = {Looking for the inner music : Probing LLMs’ understanding of literary style},
journal = {Computational Humanities Research},
year = {2025},
doi = {10.1017/chr.2025.10003}
}
EUVIMED