Words Matter

Milan Kořínek & Kamila Štekerová

Journal of Cases on Information Technology2026https://doi.org/10.4018/jcit.398628article
ABDC C
Weight
0.50

What the paper says

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.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.4018/jcit.398628

Or copy a formatted citation

@article{milan2026,
  title        = {{Words Matter}},
  author       = {Milan Kořínek & Kamila Štekerová},
  journal      = {Journal of Cases on Information Technology},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.4018/jcit.398628},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Words Matter

Flags are reviewed by the Arbiter methodology team within 5 business days.


Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.