Words Matter
Journal of Cases on Information Technology · 15.01.2026 · 28 (1) · 1-28
DOI: 10.4018/jcit.398628 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Cases on Information Technology, erschienen am 15.01.2026. Verfasst von Milan Kořínek und 1 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
This study investigates how linguistic framing influences the strategic behaviour of large language models in repeated interactions. Four models (Mistral, Qwen3, Llama3.2, Llama3.3) were embedded as autonomous agents in a simulation of a 25-round iterated prisoner's dilemma under three prompt conditions: neutral, positively biased, and hunger-framed. Although payoff structures remained constant, linguistic variation produced substantial behavioural divergence. A one-way analysis of variance showed significant prompt effects in 13 out of 16 model pairings (adjusted p < 0.05). Positively biased prompts increased cooperation by 4–9 percentage points, while survival-framed prompts increased cooperation up to 80 percentage points. While Qwen3 and Llama3.3 were highly sensitive to framing, Llama3.2 showed minimal responsiveness. Several models exhibited emergent strategies such as conditional cooperation and end-game defection. These findings indicate that subtle linguistic cues can systematically modulate cooperative behaviour in large language model agents.
Zitieren
APA
Kořínek, M., & Štekerová, K. (2026). Words Matter. Journal of Cases on Information Technology, 28(1), 1-28. https://doi.org/10.4018/jcit.398628
Vancouver
Kořínek M, Štekerová K. Words Matter. Journal of Cases on Information Technology. 2026;28(1):1-28. doi:10.4018/jcit.398628
BibTeX
@article{Konek2026,
author = {Kořínek, Milan and Štekerová, Kamila},
title = {Words Matter},
journal = {Journal of Cases on Information Technology},
year = {2026},
volume = {28},
number = {1},
pages = {1--28},
doi = {10.4018/jcit.398628}
}
EUVIMED